Trading environnement for RL agents, backtesting and training.

Overview

TradzQAI

Trading environnement for RL agents, backtesting and training.

Live session with coinbasepro-python is finaly arrived !

  • Available sessions:

    • Local
      • 1M bar datasets any size.
        • header should be ['Time', 'Open', 'High', 'Low', 'Close', 'Volume'] with ';' as separator
      • Tick datasets any size.
        • header should be ['Time', 'BID', 'ASK', 'VOL'] or ['Time', 'Price', 'Volume'] with ',' as separator
    • Live
      • Gdax API
  • Available agents:

    • DDPG
    • DQFD
    • DQN
    • DQNN
    • NAF
    • PPO
    • TRPO
    • VPG
  • Available contract type:

    • CFD
    • Classic

TradzQAI has been inspired by q-trader.

Indicators lib come from pyti

More datasets available here

Status

Alpha in development
    GUI rework on track

Getting Started

  • Dependencies :

    Installation :

    pip install -r requirements.txt

  • Running the project

    Usage:
      python run.py -h (Show usage)
      python run.py -b agent_name (to manually build config file, it build config files from agent, default PPO)
      python run.py -s live (for live session) 
      python run.py -m eval (for eval mode)
      python run.py -c config_dir/ # load config from directory, make sure you have agent, env and network json files in it
      python run.py (Run as default)
    

    When you run it for the first time, a config directory is created, you can change it to changes environnement settings and some agents settings. It save settings (env, agent, network) in a save directory, and create a new directory if make any changes.

    • Do you own decision function for maker side. For more info look at this function

      from core import Local_session as Session
      from mymodule import myfunc
      session = Session(mode=args.mode, config=args.config)
      session.initApi(key=key, b64=b64, passphrase=passphrase, url=url,
              product_id=product_id)
      session.getApi().setBestPriceFunc(myfunc)
    • Do your own runner.

    from core import Local_session as Session
    session = Session() # Run with default values
    session.loadSession() # loading environnement, worker and agent
    session.start() # Start the session thread
    • Do your own worker.
    from core import Local_env
    env = Local_env() # run with default values
    for e in episode:
      state = env.reset()
      for s in step:
        action = agent.act(state)
        next_state, terminal, reward = env.execute(action)
        agent.observe(reward, terminal)
        if terminal or env.stop:
          break
      if env.stop or e == episode - 1:
        env.logger._running = False #Close the logger thread
        break
    • How to use networks.
      • You have to define your input to fit with columns name of your datasets, it will automaticaly it grab input from network and compare it with your dataset columns in getState function, it allow you to do complex network like this :

        [
            [
                {"names": ["Price"], "type": "input"},
                {"activation": "relu", "size": 8, "type": "dense"},
                {"activation": "relu", "size": 8, "type": "dense"},
                {"name": "pricenet", "type": "output"}
            ],
            [
                {"names": ["Volume"], "type": "input"},
                {"activation": "relu", "size": 8, "type": "dense"},
                {"activation": "relu", "size": 8, "type": "dense"},
                {"name": "volnet", "type": "output"}
            ],
            [
                {"names": ["pricenet", "volnet"], "type": "input"},
                {"activation": "relu", "size": 64, "type": "dense"},
                {"activation": "relu", "size": 32, "type": "dense"},
                {"activation": "relu", "size": 8, "type": "dense"},
                {"name": "prediction", "type": "output"}
            ]
        ]
        • Simple network are handled as well without defining any input:
          [
              {"activation": "relu", "size": 64, "type": "dense"},
              {"activation": "relu", "size": 64, "type": "dense"}
          ]
    • Also TradzQAI support pre trained keras model:
      • You can build settings for your model by using py run.py -b DEEP. Your model have to be placed in the same directory as the one you use to launch it and have to be called deep_model.h5.

Relevant project

This project isn't perfect so keep this in mind.

THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

Comments
  • We cant afford any contract. Please check wallet settings.

    We cant afford any contract. Please check wallet settings.

    Hi, i encountered another issue using the new code. I tried to increase the capital from 200 to 20000 (for example) and it still happened the same way. Any idea? Thanks.

    /TradzQAI-master$ python3.6 run.py -m train DAT_ASCII_GRXEUR_M1_201711.csv : 0%| | 0/1 [00:00<?, ?it/sException in thread Thread-4: | 0/1 [00:00<?, ?it/s] Traceback (most recent call last): | 0/18354 [00:00<?, ?it/s] File "/usr/lib/python3.6/threading.py", line 916, in _bootstrap_inner self.run() File "/usr/lib/python3.6/threading.py", line 864, in run self._target(*self._args, **self._kwargs) File "/home/lamhk/TradzQAI-master/core/worker/local_worker.py", line 45, in run self.step() File "/home/lamhk/TradzQAI-master/core/worker/local_worker.py", line 71, in step state, terminal, reward = self.env.execute(action) File "/home/lamhk/TradzQAI-master/core/environnement/local_env.py", line 184, in execute self.wallet.manage_exposure(self.contract_settings) File "/home/lamhk/TradzQAI-master/core/environnement/base/wallet.py", line 197, in manage_exposure raise ValueError('current_max_pos : {:.3f} We cant afford any contract. Please check wallet settings.'.format(self.risk_managment['current_max_pos'])) ValueError: current_max_pos : 0.000 We cant afford any contract. Please check wallet settings.

    DAT_ASCII_GRXEUR_M1_201711.csv : 100%|████████████| 1/1 [00:00<00:00, 5.25it/s]

    Regards, lamhk

    question 
    opened by lamhk 9
  • How to change the agent type?

    How to change the agent type?

    Hi, I tried to build "-b BUILD" using DQN instead of PPO inside run.py line-10 / agent = "PPO". However, when I try to run the run.py, it still create directory for PPO_n. Where I should change it to switch the agent effectively. Thanks.

    question 
    opened by lamhk 6
  • command 'wc -1 data/BTC_EUR_2018_07/BTC_EUR_2018_07_01.csv' returned a non-zero exit status 1

    command 'wc -1 data/BTC_EUR_2018_07/BTC_EUR_2018_07_01.csv' returned a non-zero exit status 1

    Hi, i tried to run the code without any argument and i had this error : Command 'wc -1 data/BTC_EUR_2018_07/BTC_EUR_2018_07_01.csv' returned a non-zero exit status 1

    Do you know how to fix it?

    question 
    opened by greg2paris 5
  •  We cant afford any contract.

    We cant afford any contract.

    I get this error even though i set the wallet to a high amount. Can anybody help?

    File "C:\Users\Miner_cunt\projects\TradzQAI\TradzQAI\core\environnement\base\wallet.py", line 199, in manage_exposure raise ValueError('current_max_pos : {:.3f} We cant afford any contract. Please check wallet settings.'.format(self.risk_managment['current_max_pos'])) ValueError: current_max_pos : 0.000 We cant afford any contract. Please check wallet settings.

    Thanks

    duplicate question 
    opened by dropcunt 3
  • Exception when running live version

    Exception when running live version

    I created a config for the PPO agent and trained it on the provided data without problems.

    When I run 'python run.py -s live' I get the exception

      File "run.py", line 110, in <module>
        session.loadSession()
      File "/Users/Oscar/Documents/Cryptotrading/Tradz/TradzQAI/core/session/live.py", line 61, in loadSession
        self.initAgent()
      File "/Users/Oscar/Documents/Cryptotrading/Tradz/TradzQAI/core/session/live.py", line 74, in initAgent
        self.agent = self.agent(env=self.env, device=self.device)._get()
      File "/Users/Oscar/Documents/Cryptotrading/Tradz/TradzQAI/agents/PPO.py", line 6, in __init__
        Agent.__init__(self, env=env, device=device)
      File "/Users/Oscar/Documents/Cryptotrading/Tradz/TradzQAI/agents/agent.py", line 24, in __init__
        states=self.env.states,
    AttributeError: 'Live_env' object has no attribute 'states'
    

    I made sure my api-key, pass and secret are correct. I am connecting to https://api.pro.coinbase.com as endpoint.

    Anything I missed?

    bug 
    opened by oscarberonius 3
  • Training on GPU

    Training on GPU

    when I set the device to my GPU in run.py i get the following error:

    InvalidArgumentError (see above for traceback): Cannot assign a device for operation 'ppo/initialize/action-action/Initializer/zeros': Could not satisfy explicit device specification '' because the node was colocated with a group of nodes that required incompatible device '/device:GPU:0' Colocation Debug Info: Colocation group had the following types and devices: Assign: CPU Const: CPU Fill: GPU CPU Switch: GPU CPU VariableV2: CPU Identity: GPU CPU RefSwitch: GPU CPU StridedSliceAssign: GPU CPU IsVariableInitialized: CPU

    Does anybody has the same issue? Do you know were you can set something like allow_soft_placement=True? Thanks for your help!

    question 
    opened by dropcunt 2
  • Choosing different agent than PPO produces faulty behavior.

    Choosing different agent than PPO produces faulty behavior.

    I can run the default agent without issues, but had some trouble when running TRPO and DQN.

    I tried removing both the save and config directories and rebuilding with trpo using 'python run.py -b TRPO'. The config directory seemed to be correctly created. The containing agent.json file had the correct property "type": "trpo_agent".

    When I tried running the agent (python run.py) a save directory containing a PPO_0 directory was created. I tried changing the default agent in run.py to be TRPO as well but had the same result. The model could not evaluate and produced the following error.

    Traceback (most recent call last):
      File "run.py", line 110, in <module>
        session.loadSession()
      File "/Users/Oscar/Documents/Cryptotrading/Tradz/TradzQAI/core/session/local.py", line 46, in loadSession
        self.initAgent()
      File "/Users/Oscar/Documents/Cryptotrading/Tradz/TradzQAI/core/session/local.py", line 57, in initAgent
        self.agent = self.agent(env=self.env, device=self.device)._get()
      File "/Users/Oscar/Documents/Cryptotrading/Tradz/TradzQAI/agents/PPO.py", line 6, in __init__
        Agent.__init__(self, env=env, device=device)
      File "/Users/Oscar/Documents/Cryptotrading/Tradz/TradzQAI/agents/agent.py", line 27, in __init__
        device=device
      File "/Users/Oscar/Documents/Cryptotrading/Tradz/lib/python3.6/site-packages/tensorforce/agents/agent.py", line 283, in from_spec
        kwargs=kwargs
      File "/Users/Oscar/Documents/Cryptotrading/Tradz/lib/python3.6/site-packages/tensorforce/util.py", line 192, in get_object
        return obj(*args, **kwargs)
      File "/Users/Oscar/Documents/Cryptotrading/Tradz/lib/python3.6/site-packages/tensorforce/agents/trpo_agent.py", line 161, in __init__
        entropy_regularization=entropy_regularization
      File "/Users/Oscar/Documents/Cryptotrading/Tradz/lib/python3.6/site-packages/tensorforce/agents/learning_agent.py", line 141, in __init__
        batching_capacity=batching_capacity
      File "/Users/Oscar/Documents/Cryptotrading/Tradz/lib/python3.6/site-packages/tensorforce/agents/agent.py", line 80, in __init__
        self.model = self.initialize_model()
      File "/Users/Oscar/Documents/Cryptotrading/Tradz/lib/python3.6/site-packages/tensorforce/agents/trpo_agent.py", line 189, in initialize_model
        likelihood_ratio_clipping=self.likelihood_ratio_clipping
      File "/Users/Oscar/Documents/Cryptotrading/Tradz/lib/python3.6/site-packages/tensorforce/models/pg_prob_ratio_model.py", line 88, in __init__
        gae_lambda=gae_lambda
      File "/Users/Oscar/Documents/Cryptotrading/Tradz/lib/python3.6/site-packages/tensorforce/models/pg_model.py", line 98, in __init__
        requires_deterministic=False
      File "/Users/Oscar/Documents/Cryptotrading/Tradz/lib/python3.6/site-packages/tensorforce/models/distribution_model.py", line 90, in __init__
        discount=discount
      File "/Users/Oscar/Documents/Cryptotrading/Tradz/lib/python3.6/site-packages/tensorforce/models/memory_model.py", line 114, in __init__
        reward_preprocessing=reward_preprocessing
      File "/Users/Oscar/Documents/Cryptotrading/Tradz/lib/python3.6/site-packages/tensorforce/models/model.py", line 217, in __init__
        self.setup()
      File "/Users/Oscar/Documents/Cryptotrading/Tradz/lib/python3.6/site-packages/tensorforce/models/model.py", line 290, in setup
        independent=independent
      File "/Users/Oscar/Documents/Cryptotrading/Tradz/lib/python3.6/site-packages/tensorforce/models/memory_model.py", line 605, in create_operations
        independent=independent
      File "/Users/Oscar/Documents/Cryptotrading/Tradz/lib/python3.6/site-packages/tensorforce/models/model.py", line 1195, in create_operations
        self.create_observe_operations(reward=reward, terminal=terminal)
      File "/Users/Oscar/Documents/Cryptotrading/Tradz/lib/python3.6/site-packages/tensorforce/models/model.py", line 1129, in create_observe_operations
        reward=reward
      File "/Users/Oscar/Documents/Cryptotrading/Tradz/lib/python3.6/site-packages/tensorflow/python/ops/template.py", line 368, in __call__
        return self._call_func(args, kwargs)
      File "/Users/Oscar/Documents/Cryptotrading/Tradz/lib/python3.6/site-packages/tensorflow/python/ops/template.py", line 311, in _call_func
        result = self._func(*args, **kwargs)
      File "/Users/Oscar/Documents/Cryptotrading/Tradz/lib/python3.6/site-packages/tensorforce/models/memory_model.py", line 566, in tf_observe_timestep
        return tf.cond(pred=optimize, true_fn=true_fn, false_fn=tf.no_op)
      File "/Users/Oscar/Documents/Cryptotrading/Tradz/lib/python3.6/site-packages/tensorflow/python/util/deprecation.py", line 488, in new_func
        return func(*args, **kwargs)
      File "/Users/Oscar/Documents/Cryptotrading/Tradz/lib/python3.6/site-packages/tensorflow/python/ops/control_flow_ops.py", line 2076, in cond
        orig_res_t, res_t = context_t.BuildCondBranch(true_fn)
      File "/Users/Oscar/Documents/Cryptotrading/Tradz/lib/python3.6/site-packages/tensorflow/python/ops/control_flow_ops.py", line 1920, in BuildCondBranch
        original_result = fn()
      File "/Users/Oscar/Documents/Cryptotrading/Tradz/lib/python3.6/site-packages/tensorforce/models/memory_model.py", line 562, in true_fn
        optimize = self.fn_optimization(**batch)
      File "/Users/Oscar/Documents/Cryptotrading/Tradz/lib/python3.6/site-packages/tensorflow/python/ops/template.py", line 368, in __call__
        return self._call_func(args, kwargs)
      File "/Users/Oscar/Documents/Cryptotrading/Tradz/lib/python3.6/site-packages/tensorflow/python/ops/template.py", line 311, in _call_func
        result = self._func(*args, **kwargs)
      File "/Users/Oscar/Documents/Cryptotrading/Tradz/lib/python3.6/site-packages/tensorforce/models/pg_model.py", line 305, in tf_optimization
        next_internals=next_internals
      File "/Users/Oscar/Documents/Cryptotrading/Tradz/lib/python3.6/site-packages/tensorforce/models/memory_model.py", line 491, in tf_optimization
        return self.optimizer.minimize(**arguments)
      File "/Users/Oscar/Documents/Cryptotrading/Tradz/lib/python3.6/site-packages/tensorforce/core/optimizers/optimizer.py", line 139, in minimize
        deltas = self.step(time=time, variables=variables, **kwargs)
      File "/Users/Oscar/Documents/Cryptotrading/Tradz/lib/python3.6/site-packages/tensorflow/python/ops/template.py", line 368, in __call__
        return self._call_func(args, kwargs)
      File "/Users/Oscar/Documents/Cryptotrading/Tradz/lib/python3.6/site-packages/tensorflow/python/ops/template.py", line 311, in _call_func
        result = self._func(*args, **kwargs)
      File "/Users/Oscar/Documents/Cryptotrading/Tradz/lib/python3.6/site-packages/tensorforce/core/optimizers/optimized_step.py", line 102, in tf_step
        **kwargs
      File "/Users/Oscar/Documents/Cryptotrading/Tradz/lib/python3.6/site-packages/tensorflow/python/ops/template.py", line 368, in __call__
        return self._call_func(args, kwargs)
      File "/Users/Oscar/Documents/Cryptotrading/Tradz/lib/python3.6/site-packages/tensorflow/python/ops/template.py", line 311, in _call_func
        result = self._func(*args, **kwargs)
      File "/Users/Oscar/Documents/Cryptotrading/Tradz/lib/python3.6/site-packages/tensorforce/core/optimizers/natural_gradient.py", line 123, in tf_step
        deltas = self.solver.solve(fn_x=fisher_matrix_product, x_init=None, b=[-grad for grad in loss_gradients])
      File "/Users/Oscar/Documents/Cryptotrading/Tradz/lib/python3.6/site-packages/tensorflow/python/ops/template.py", line 368, in __call__
        return self._call_func(args, kwargs)
      File "/Users/Oscar/Documents/Cryptotrading/Tradz/lib/python3.6/site-packages/tensorflow/python/ops/template.py", line 311, in _call_func
        result = self._func(*args, **kwargs)
      File "/Users/Oscar/Documents/Cryptotrading/Tradz/lib/python3.6/site-packages/tensorforce/core/optimizers/solvers/conjugate_gradient.py", line 80, in tf_solve
        return super(ConjugateGradient, self).tf_solve(fn_x, x_init, b)
      File "/Users/Oscar/Documents/Cryptotrading/Tradz/lib/python3.6/site-packages/tensorforce/core/optimizers/solvers/iterative.py", line 78, in tf_solve
        args = tf.while_loop(cond=self.next_step, body=self.step, loop_vars=args)
      File "/Users/Oscar/Documents/Cryptotrading/Tradz/lib/python3.6/site-packages/tensorflow/python/ops/control_flow_ops.py", line 3274, in while_loop
        return_same_structure)
      File "/Users/Oscar/Documents/Cryptotrading/Tradz/lib/python3.6/site-packages/tensorflow/python/ops/control_flow_ops.py", line 2994, in BuildLoop
        pred, body, original_loop_vars, loop_vars, shape_invariants)
      File "/Users/Oscar/Documents/Cryptotrading/Tradz/lib/python3.6/site-packages/tensorflow/python/ops/control_flow_ops.py", line 2929, in _BuildLoop
        body_result = body(*packed_vars_for_body)
      File "/Users/Oscar/Documents/Cryptotrading/Tradz/lib/python3.6/site-packages/tensorflow/python/ops/template.py", line 368, in __call__
        return self._call_func(args, kwargs)
      File "/Users/Oscar/Documents/Cryptotrading/Tradz/lib/python3.6/site-packages/tensorflow/python/ops/template.py", line 311, in _call_func
        result = self._func(*args, **kwargs)
      File "/Users/Oscar/Documents/Cryptotrading/Tradz/lib/python3.6/site-packages/tensorforce/core/optimizers/solvers/conjugate_gradient.py", line 128, in tf_step
        A_conjugate = self.fn_x(conjugate)
      File "/Users/Oscar/Documents/Cryptotrading/Tradz/lib/python3.6/site-packages/tensorforce/core/optimizers/natural_gradient.py", line 112, in fisher_matrix_product
        return tf.gradients(ys=delta_kldiv_gradients, xs=variables)
      File "/Users/Oscar/Documents/Cryptotrading/Tradz/lib/python3.6/site-packages/tensorflow/python/ops/gradients_impl.py", line 596, in gradients
        gate_gradients, aggregation_method, stop_gradients)
      File "/Users/Oscar/Documents/Cryptotrading/Tradz/lib/python3.6/site-packages/tensorflow/python/ops/gradients_impl.py", line 749, in _GradientsHelper
        _RaiseNoGradWrtInitialLoopValError(op, from_ops, xs)
      File "/Users/Oscar/Documents/Cryptotrading/Tradz/lib/python3.6/site-packages/tensorflow/python/ops/gradients_impl.py", line 441, in _RaiseNoGradWrtInitialLoopValError
        % target_op.name)
    ValueError: Cannot compute gradient inside while loop with respect to op 'trpo/actions-and-internals/layered-network/apply/dense0/apply/linear/apply/W'. We do not support taking the gradient wrt or through the initial value of a loop variable. Gradients can be computed through loop invariants or wrt the input parameters to the loop body.
    

    Switching to dqn produced the same problems with the file structure, although the model could evaluate.

    bug 
    opened by oscarberonius 2
  • Using other exchanges

    Using other exchanges

    Is it possible to change the exchanges for the life exchanges? Where to start? If you give me a starting point i could try and do it myself and make a pull request afterwards

    opened by AlconDivino 1
  • complex network

    complex network "names" issue

    When I try to change the network to a complex network I get this error:

    File "/Users/dropper/projects/crypto_bot/tforce_btc_trader/tensorforce/tensorforce/util.py", line 159, in get_object return obj(*args, **kwargs) TypeError: __init__() got an unexpected keyword argument 'names'

    Do I have to change something in the dataloader.py?

    Thank you

    opened by LucaKern 1
  • Performing training automatically evaluates the model.

    Performing training automatically evaluates the model.

    So I have a little trouble understanding how the training/evaluation works.

    If I run 'python run.py -m train', a log file "train_date.txt" is created with the resulting award in /save/agent_#. Likewise a log file "eval_date.txt" is created when I run the evaluation command.

    I can run the eval command and get results even without running the training command first. The results of the evaluation seem to be the same regardless of how many times the evaluation is run, but the results of the training differ every time.

    Can you explain what the difference is and what data is being used to evaluate the model? To me it seems like both commands train a model on all the provided data and then evaluate on parts of that same data, but I can't figure out what really is happening.

    question 
    opened by oscarberonius 1
  • Cannot modify training data

    Cannot modify training data

    Hi.

    I can successfully run the PPO agent using the provided file structure of the data directory. For this I am using "data_directory": "data/" as argument in environnement.json.

    However, I tried pulling out the directory BTC_EUR_2018_07 and placed it in a new directory eval_data at the same level as the data dir. Now when I do 'python run.py -m train' I get the following error.

      File "run.py", line 110, in <module>
        session.loadSession()
      File "/Users/Oscar/Documents/Cryptotrading/Tradz/TradzQAI/core/session/local.py", line 46, in loadSession
        self.initAgent()
      File "/Users/Oscar/Documents/Cryptotrading/Tradz/TradzQAI/core/session/local.py", line 57, in initAgent
        self.agent = self.agent(env=self.env, device=self.device)._get()
      File "/Users/Oscar/Documents/Cryptotrading/Tradz/TradzQAI/agents/PPO.py", line 6, in __init__
        Agent.__init__(self, env=env, device=device)
      File "/Users/Oscar/Documents/Cryptotrading/Tradz/TradzQAI/agents/agent.py", line 27, in __init__
        device=device
      File "/Users/Oscar/Documents/Cryptotrading/Tradz/lib/python3.6/site-packages/tensorforce/agents/agent.py", line 283, in from_spec
        kwargs=kwargs
      File "/Users/Oscar/Documents/Cryptotrading/Tradz/lib/python3.6/site-packages/tensorforce/util.py", line 192, in get_object
        return obj(*args, **kwargs)
      File "/Users/Oscar/Documents/Cryptotrading/Tradz/lib/python3.6/site-packages/tensorforce/agents/ppo_agent.py", line 155, in __init__
        entropy_regularization=entropy_regularization
      File "/Users/Oscar/Documents/Cryptotrading/Tradz/lib/python3.6/site-packages/tensorforce/agents/learning_agent.py", line 141, in __init__
        batching_capacity=batching_capacity
      File "/Users/Oscar/Documents/Cryptotrading/Tradz/lib/python3.6/site-packages/tensorforce/agents/agent.py", line 80, in __init__
        self.model = self.initialize_model()
      File "/Users/Oscar/Documents/Cryptotrading/Tradz/lib/python3.6/site-packages/tensorforce/agents/ppo_agent.py", line 183, in initialize_model
        likelihood_ratio_clipping=self.likelihood_ratio_clipping
      File "/Users/Oscar/Documents/Cryptotrading/Tradz/lib/python3.6/site-packages/tensorforce/models/pg_prob_ratio_model.py", line 88, in __init__
        gae_lambda=gae_lambda
      File "/Users/Oscar/Documents/Cryptotrading/Tradz/lib/python3.6/site-packages/tensorforce/models/pg_model.py", line 98, in __init__
        requires_deterministic=False
      File "/Users/Oscar/Documents/Cryptotrading/Tradz/lib/python3.6/site-packages/tensorforce/models/distribution_model.py", line 90, in __init__
        discount=discount
      File "/Users/Oscar/Documents/Cryptotrading/Tradz/lib/python3.6/site-packages/tensorforce/models/memory_model.py", line 114, in __init__
        reward_preprocessing=reward_preprocessing
      File "/Users/Oscar/Documents/Cryptotrading/Tradz/lib/python3.6/site-packages/tensorforce/models/model.py", line 217, in __init__
        self.setup()
      File "/Users/Oscar/Documents/Cryptotrading/Tradz/lib/python3.6/site-packages/tensorforce/models/model.py", line 242, in setup
        self.setup_placeholders()
      File "/Users/Oscar/Documents/Cryptotrading/Tradz/lib/python3.6/site-packages/tensorforce/models/model.py", line 448, in setup_placeholders
        kwargs=dict(shape=self.states_spec[name]['shape']))
    UnboundLocalError: local variable 'name' referenced before assignment
    

    Any idea?

    question 
    opened by oscarberonius 1
  • Bump numpy from 1.14.5 to 1.22.0

    Bump numpy from 1.14.5 to 1.22.0

    Bumps numpy from 1.14.5 to 1.22.0.

    Release notes

    Sourced from numpy's releases.

    v1.22.0

    NumPy 1.22.0 Release Notes

    NumPy 1.22.0 is a big release featuring the work of 153 contributors spread over 609 pull requests. There have been many improvements, highlights are:

    • Annotations of the main namespace are essentially complete. Upstream is a moving target, so there will likely be further improvements, but the major work is done. This is probably the most user visible enhancement in this release.
    • A preliminary version of the proposed Array-API is provided. This is a step in creating a standard collection of functions that can be used across application such as CuPy and JAX.
    • NumPy now has a DLPack backend. DLPack provides a common interchange format for array (tensor) data.
    • New methods for quantile, percentile, and related functions. The new methods provide a complete set of the methods commonly found in the literature.
    • A new configurable allocator for use by downstream projects.

    These are in addition to the ongoing work to provide SIMD support for commonly used functions, improvements to F2PY, and better documentation.

    The Python versions supported in this release are 3.8-3.10, Python 3.7 has been dropped. Note that 32 bit wheels are only provided for Python 3.8 and 3.9 on Windows, all other wheels are 64 bits on account of Ubuntu, Fedora, and other Linux distributions dropping 32 bit support. All 64 bit wheels are also linked with 64 bit integer OpenBLAS, which should fix the occasional problems encountered by folks using truly huge arrays.

    Expired deprecations

    Deprecated numeric style dtype strings have been removed

    Using the strings "Bytes0", "Datetime64", "Str0", "Uint32", and "Uint64" as a dtype will now raise a TypeError.

    (gh-19539)

    Expired deprecations for loads, ndfromtxt, and mafromtxt in npyio

    numpy.loads was deprecated in v1.15, with the recommendation that users use pickle.loads instead. ndfromtxt and mafromtxt were both deprecated in v1.17 - users should use numpy.genfromtxt instead with the appropriate value for the usemask parameter.

    (gh-19615)

    ... (truncated)

    Commits

    Dependabot compatibility score

    Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.


    Dependabot commands and options

    You can trigger Dependabot actions by commenting on this PR:

    • @dependabot rebase will rebase this PR
    • @dependabot recreate will recreate this PR, overwriting any edits that have been made to it
    • @dependabot merge will merge this PR after your CI passes on it
    • @dependabot squash and merge will squash and merge this PR after your CI passes on it
    • @dependabot cancel merge will cancel a previously requested merge and block automerging
    • @dependabot reopen will reopen this PR if it is closed
    • @dependabot close will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually
    • @dependabot ignore this major version will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)
    • @dependabot ignore this minor version will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)
    • @dependabot ignore this dependency will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)
    • @dependabot use these labels will set the current labels as the default for future PRs for this repo and language
    • @dependabot use these reviewers will set the current reviewers as the default for future PRs for this repo and language
    • @dependabot use these assignees will set the current assignees as the default for future PRs for this repo and language
    • @dependabot use this milestone will set the current milestone as the default for future PRs for this repo and language

    You can disable automated security fix PRs for this repo from the Security Alerts page.

    dependencies 
    opened by dependabot[bot] 0
  • base_env.py check_time_before_closing() idx not defined

    base_env.py check_time_before_closing() idx not defined

    I loaded a Dataset with LTCUSDT data from binance (Format: Timestamp;Open;Low,High;Close;Volume) I now got the following error:

    agent not loaded
    binanceData_LTCUSDT_1m.csv :   0%|                        | 0/1 [00:00<?, ?it/sException in thread Thread-3:                              | 0/1 [00:00<?, ?it/s]
    Traceback (most recent call last):█████▉| 200994/200998 [54:19<00:00, 27.90it/s]
      File "/usr/lib/python3.6/threading.py", line 916, in _bootstrap_inner
        self.run()
      File "/usr/lib/python3.6/threading.py", line 864, in run
        self._target(*self._args, **self._kwargs)
      File "/home/alcon/Desktop/TradzQAI/TradzQAI/core/worker/local_worker.py", line 23, in run
        self.step()
      File "/home/alcon/Desktop/TradzQAI/TradzQAI/core/worker/local_worker.py", line 46, in step
        state, terminal, reward = self.env.execute(action)
      File "/home/alcon/Desktop/TradzQAI/TradzQAI/core/environnement/local_env.py", line 178, in execute
        self.check_time_before_closing()
      File "/home/alcon/Desktop/TradzQAI/TradzQAI/core/environnement/base/base_env.py", line 148, in check_time_before_closing
        self.step_left = idx - self.current_step['step'] + 1
    UnboundLocalError: local variable 'idx' referenced before assignment
    
    binanceData_LTCUSDT_1m.csv : 100%|██████████████| 1/1 [54:19<00:00, 3259.48s/it]
    ^[[A Processing : 100%|████████████████▉| 200996/200998 [54:19<00:00, 61.67it/s]
    
    
    

    Looking at the function i see that the runnervar idx is really not defined in the last line. I then defined the var at the begining as idx=0

        def check_time_before_closing(self):
            if self.current_step['step'] == self.len_data - 1:
                return
            for idx in range(self.current_step['step'] + 1 , self.len_data - 1):
                if self._date[idx - 1][7] != self._date[idx][7]:
                    break
            self.step_left = idx - self.current_step['step'] + 1
    

    The process ran smothly with my own data and the dax data in the repo but when running python3 run.py -m eval and checking the save logs everything is 0 like this:

    2019:04:09 17:47:40 000000 Starting episode : 1
    2019:04:09 17:47:56 000001 ######################################################
    2019:04:09 17:47:56 000002 Total reward : 0
    2019:04:09 17:47:56 000003 Average reward : 0.000
    2019:04:09 17:47:56 000004 Avg reward 500 : 0.0
    2019:04:09 17:47:56 000005 Avg reward 100 : 0.0
    2019:04:09 17:47:56 000006 Avg reward 50 : 0.0
    2019:04:09 17:47:56 000007 Avg reward 10 : 0.0
    2019:04:09 17:47:56 000008 Total profit : 0
    2019:04:09 17:47:56 000009 Total trade : 0
    2019:04:09 17:47:56 000010 Sharp ratio : 0.000
    2019:04:09 17:47:56 000011 Mean return : 0.000
    2019:04:09 17:47:56 000012 Max Drawdown : 0.000
    2019:04:09 17:47:56 000013 Max return : 0.000
    2019:04:09 17:47:56 000014 Percent return : 0.000
    2019:04:09 17:47:56 000015 Trade W/L : 0.000
    2019:04:09 17:47:56 000016 Step : 18353
    2019:04:09 17:47:56 000017 ######################################################
    

    Any idea what i can do?

    help wanted 
    opened by AlconDivino 2
  • Error

    Error

    python run.py

    Traceback (most recent call last): File "run.py", line 30, in from TradzQAI import Local_session as Session File "/home/desktop/Downloads/TradzQAI-master/TradzQAI/init.py", line 1, in from .core import Local_session File "/home/desktop/Downloads/TradzQAI-master/TradzQAI/core/init.py", line 1, in from .environnement import Local_env File "/home/desktop/Downloads/TradzQAI-master/TradzQAI/core/environnement/init.py", line 1, in from .local_env import Local_env File "/home/desktop/Downloads/TradzQAI-master/TradzQAI/core/environnement/local_env.py", line 1, in from TradzQAI.tools import act_processing File "/home/desktop/Downloads/TradzQAI-master/TradzQAI/tools/init.py", line 5, in from .utils import * File "/home/desktop/Downloads/TradzQAI-master/TradzQAI/tools/utils.py", line 22 SyntaxError: Non-ASCII character '\xe2' in file /home/desktop/Downloads/TradzQAI-master/TradzQAI/tools/utils.py on line 22, but no encoding declared; see http://python.org/dev/peps/pep-0263/ for details

    question 
    opened by ghost 3
  • live session error

    live session error

    I have this problem when run with the live session:

      File "run.py", line 42, in <module>
        product_id=product_id)
      File "C:\Users\dannox\Google Drive\stockOptionsTrading\TradzQAI\TradzQAI\core\session\live.py", line 119, in initApi
        self.initEnv()
      File "C:\Users\dannox\Google Drive\stockOptionsTrading\TradzQAI\TradzQAI\core\session\live.py", line 124, in initEnv
        logger=self.logger, saver=self.saver, dataloader=self.dl, api=self.api)
      File "C:\Users\dannox\Google Drive\stockOptionsTrading\TradzQAI\TradzQAI\core\environnement\live_env.py", line 99, in __init__
        self.dl.loadHistorical()
      File "C:\Users\dannox\Google Drive\stockOptionsTrading\TradzQAI\TradzQAI\core\environnement\base\dataloader.py", line 245, in loadHistorical
        self.ticks = tick.join(self.indics.build_indicators(tick['Price']))
      File "C:\Users\dannox\Google Drive\stockOptionsTrading\TradzQAI\TradzQAI\tools\indicators\build_indicators.py", line 76, in build_indicators
        indicators[idx[1]] = idx[0](data, idx[2][0], idx[2][1])
      File "C:\Users\dannox\Google Drive\stockOptionsTrading\TradzQAI\TradzQAI\tools\indicators\moving_average_convergence_divergence.py", line 12, in moving_average_convergence_divergence
        check_for_period_error(data, long_period)
      File "C:\Users\dannox\Google Drive\stockOptionsTrading\TradzQAI\TradzQAI\tools\indicators\catch_errors.py", line 14, in check_for_period_error
        raise Exception("Error: data_len < period")
    Exception: Error: data_len < period
    Error: messages missing (4948236479 - 4948236523). Re-initializing  book at sequence.
    
    bug 
    opened by dgiunchi 1
  • Possible bug in dataloader.py

    Possible bug in dataloader.py

    Hi,

    I ran into a problem when I tried running the new core. I successfully built the PPO agent, but when I executed an eval session I received the following exception.

    #PRINT# lines.split(sep) = ['20180701000108', '5467.87', '0.062', '56.86932808248668', '1.828228906843833', '0.12368473729161092', '5468.798899294792', '5457.467818250765', '5444.815160592744']
    Traceback (most recent call last):
      File "run.py", line 42, in <module>
        session.loadSession()
      File "/Users/Oscar/Documents/Cryptotrading/Tradz/TradzQAI/TradzQAI/core/session/local.py", line 71, in loadSession
        self.initEnv()
      File "/Users/Oscar/Documents/Cryptotrading/Tradz/TradzQAI/TradzQAI/core/session/local.py", line 102, in initEnv
        logger=self.logger, saver=self.saver, dataloader=self.dl)
      File "/Users/Oscar/Documents/Cryptotrading/Tradz/TradzQAI/TradzQAI/core/environnement/local_env.py", line 84, in __init__
        self.dl.loadFile()
      File "/Users/Oscar/Documents/Cryptotrading/Tradz/TradzQAI/TradzQAI/core/environnement/base/dataloader.py", line 177, in loadFile
        tmp_data, tmp_raw, tmp_time = self.getStockDataVec(self.files[self.files_index])
      File "/Users/Oscar/Documents/Cryptotrading/Tradz/TradzQAI/TradzQAI/core/environnement/base/dataloader.py", line 150, in getStockDataVec
        df.columns = names
    UnboundLocalError: local variable 'names' referenced before assignment
    

    I'm not sure if the code is supposed to be able to handle a row length of 10 or not, but there shouldn't be any problem with the data as I tested it before and made sure the path is correct.

    enhancement 
    opened by oscarberonius 5
Releases(v0.2)
  • v0.2(Dec 19, 2017)

    • Moved GUI to PyQT5

    • 1 month data saved

      • DAX30 2017 10
    • multiple agents implemented

      • DQN
      • DDQN
      • DRQN
      • DDRQN
    • Added some managment fonction

      • Wallet managment
      • Risk managment
      • Close position on better profit
    Source code(tar.gz)
    Source code(zip)
  • v0.1(Dec 19, 2017)

    • Tkinter GUI

      • Start window with some settings
      • Overview window with some view on env, and model behaviour
    • 1 month data without saved model

      • DAX30
    • Just one agent (DQN)

    • Takes long and short positions

    Source code(tar.gz)
    Source code(zip)
Owner
Tony Denion
Machine learning engineer.
Tony Denion
Trading and Backtesting environment for training reinforcement learning agent or simple rule base algo.

TradingGym TradingGym is a toolkit for training and backtesting the reinforcement learning algorithms. This was inspired by OpenAI Gym and imitated th

Yvictor 1.1k Jan 2, 2023
A Python-based development platform for automated trading systems - from backtesting to optimisation to livetrading.

AutoTrader AutoTrader is Python-based platform intended to help in the development, optimisation and deployment of automated trading systems. From sim

Kieran Mackle 485 Jan 9, 2023
​TextWorld is a sandbox learning environment for the training and evaluation of reinforcement learning (RL) agents on text-based games.

TextWorld A text-based game generator and extensible sandbox learning environment for training and testing reinforcement learning (RL) agents. Also ch

Microsoft 983 Dec 23, 2022
ManiSkill-Learn is a framework for training agents on SAPIEN Open-Source Manipulation Skill Challenge (ManiSkill Challenge), a large-scale learning-from-demonstrations benchmark for object manipulation.

ManiSkill-Learn ManiSkill-Learn is a framework for training agents on SAPIEN Open-Source Manipulation Skill Challenge, a large-scale learning-from-dem

Hao Su's Lab, UCSD 48 Dec 30, 2022
A general-purpose, flexible, and easy-to-use simulator alongside an OpenAI Gym trading environment for MetaTrader 5 trading platform (Approved by OpenAI Gym)

gym-mtsim: OpenAI Gym - MetaTrader 5 Simulator MtSim is a simulator for the MetaTrader 5 trading platform alongside an OpenAI Gym environment for rein

Mohammad Amin Haghpanah 184 Dec 31, 2022
Trading Gym is an open source project for the development of reinforcement learning algorithms in the context of trading.

Trading Gym Trading Gym is an open-source project for the development of reinforcement learning algorithms in the context of trading. It is currently

Dimitry Foures 535 Nov 15, 2022
Scalable, event-driven, deep-learning-friendly backtesting library

...Minimizing the mean square error on future experience. - Richard S. Sutton BTGym Scalable event-driven RL-friendly backtesting library. Build on

Andrew 922 Dec 27, 2022
Certis - Certis, A High-Quality Backtesting Engine

Certis - Backtesting For y'all Certis is a powerful, lightweight, simple backtes

Yeachan-Heo 46 Oct 30, 2022
A user-friendly research and development tool built to standardize RL competency assessment for custom agents and environments.

Built with ❤️ by Sam Showalter Contents Overview Installation Dependencies Usage Scripts Standard Execution Environment Development Environment Benchm

SRI-AIC 1 Nov 18, 2021
Train robotic agents to learn pick and place with deep learning for vision-based manipulation in PyBullet.

Ravens is a collection of simulated tasks in PyBullet for learning vision-based robotic manipulation, with emphasis on pick and place. It features a Gym-like API with 10 tabletop rearrangement tasks, each with (i) a scripted oracle that provides expert demonstrations (for imitation learning), and (ii) reward functions that provide partial credit (for reinforcement learning).

Google Research 367 Jan 9, 2023
A lightweight Python-based 3D network multi-agent simulator. Uses a cell-based congestion model. Calculates risk, loudness and battery capacities of the agents. Suitable for 3D network optimization tasks.

AMAZ3DSim AMAZ3DSim is a lightweight python-based 3D network multi-agent simulator. It uses a cell-based congestion model. It calculates risk, battery

Daniel Hirsch 13 Nov 4, 2022
Pacman-AI - AI project designed by UC Berkeley. Designed reflex and minimax agents for the game Pacman.

Pacman AI Jussi Doherty CAP 4601 - Introduction to Artificial Intelligence - Fall 2020 Python version 3.0+ Source of this project This repo contains a

Jussi Doherty 1 Jan 3, 2022
Lux AI environment interface for RLlib multi-agents

Lux AI interface to RLlib MultiAgentsEnv For Lux AI Season 1 Kaggle competition. LuxAI repo RLlib-multiagents docs Kaggle environments repo Please let

Jaime 12 Nov 7, 2022
PyTorch implementation of our ICCV 2021 paper, Interpretation of Emergent Communication in Heterogeneous Collaborative Embodied Agents.

PyTorch implementation of our ICCV 2021 paper, Interpretation of Emergent Communication in Heterogeneous Collaborative Embodied Agents.

Saim Wani 4 May 8, 2022
An example project demonstrating how the Autonomous Learning Library can be used to build new reinforcement learning agents.

About This repository shows how Autonomous Learning Library can be used to build new reinforcement learning agents. In particular, it contains a model

Chris Nota 5 Aug 30, 2022
Fake-user-agent-traffic-geneator - Python CLI Tool to generate fake traffic against URLs with configurable user-agents

Fake traffic generator for Gartner Demo Generate fake traffic to URLs with custo

New Relic Experimental 3 Oct 31, 2022
A resource for learning about deep learning techniques from regression to LSTM and Reinforcement Learning using financial data and the fitness functions of algorithmic trading

A tour through tensorflow with financial data I present several models ranging in complexity from simple regression to LSTM and policy networks. The s

null 195 Dec 7, 2022
This is the code for our KILT leaderboard submission to the T-REx and zsRE tasks. It includes code for training a DPR model then continuing training with RAG.

KGI (Knowledge Graph Induction) for slot filling This is the code for our KILT leaderboard submission to the T-REx and zsRE tasks. It includes code fo

International Business Machines 72 Jan 6, 2023
This project uses reinforcement learning on stock market and agent tries to learn trading. The goal is to check if the agent can learn to read tape. The project is dedicated to hero in life great Jesse Livermore.

Reinforcement-trading This project uses Reinforcement learning on stock market and agent tries to learn trading. The goal is to check if the agent can

Deepender Singla 1.4k Dec 22, 2022