Conservative and Adaptive Penalty for Model-Based Safe Reinforcement Learning

Related tags

Deep Learning CAP
Overview

Conservative and Adaptive Penalty for Model-Based Safe Reinforcement Learning

This is the official repository for Conservative and Adaptive Penalty for Model-Based Safe Reinforcement Learning. We provide the commands to run the PETS and PlaNet experiments included in the paper. This repository is made minimal for ease of experimentation.

Installations

This repository requires Python (3.6), Pytorch (version 1.3 or above) run the following command to create a conda environment (tested using CUDA10.2):

conda env create -f environment.yml

Experiments

To run the PETS experiments on the HalfCheetah environment used in our ablation study, run:

cd cap-pets

CAP

python cap-pets/run_cap_pets.py --algo cem --env HalfCheetah-v3 --cost_lim 152 \
--cost_constrained --penalize_uncertainty --learn_kappa --seed 1

CAP with fixed kappa

python cap-pets/run_cap_pets.py --algo cem --env HalfCheetah-v3 --cost_lim 152 \
--cost_constrained --penalize_uncertainty --kappa 1.0 --seed 1

CCEM

python cap-pets/run_cap_pets.py --algo cem --env HalfCheetah-v3 --cost_lim 152 \
--cost_constrained --seed 1

CEM

python cap-pets/run_cap_pets.py --algo cem --env HalfCheetah-v3 --cost_lim 152 \
--seed 1

The commands for the PlaNet experiment on the CarRacing environment are:

CAP

python cap-planet/run_cap_planet.py --env CarRacingSkiddingConstrained-v0 \
--cost-limit 0 --binary-cost \
--cost-constrained --penalize-uncertainty \
--learn-kappa --penalty-kappa 0.1 \
--id CarRacing-cap --seed 1

CAP with fixed kappa

python cap-planet/run_cap_planet.py --env CarRacingSkiddingConstrained-v0 \
--cost-limit 0 --binary-cost \
--cost-constrained --penalize-uncertainty \
--penalty-kappa 1.0 \
--id CarRacing-kappa1 --seed 1

CCEM

python cap-planet/run_cap_planet.py --env CarRacingSkiddingConstrained-v0 \
--cost-limit 0 --binary-cost \
--cost-constrained \
--id CarRacing-ccem --seed 1

CEM

python cap-planet/run_cap_planet.py --env CarRacingSkiddingConstrained-v0 \
--cost-limit 0 --binary-cost \
--id CarRacing-cem --seed 1

Contact

If you have any questions regarding the code or paper, feel free to contact [email protected] or open an issue on this repository.

Acknowledgement

This repository contains code adapted from the following repositories: PETS and PlaNet. We thank the authors and contributors for open-sourcing their code.

You might also like...
On the model-based stochastic value gradient for continuous reinforcement learning

On the model-based stochastic value gradient for continuous reinforcement learning This repository is by Brandon Amos, Samuel Stanton, Denis Yarats, a

Facebook Research 46 Dec 15, 2022
The code for the NSDI'21 paper "BMC: Accelerating Memcached using Safe In-kernel Caching and Pre-stack Processing".

BMC The code for the NSDI'21 paper "BMC: Accelerating Memcached using Safe In-kernel Caching and Pre-stack Processing". BibTex entry available here. B

Orange 383 Dec 16, 2022
A solution to ensure Crowd Management with Contactless and Safe systems.
A solution to ensure Crowd Management with Contactless and Safe systems.

CovidTrack A Solution to ensure Crowd Management with Contactless and Safe systems. ML Model Mask Detection Social Distancing Detection Analytics Page

Om Khare 1 Nov 10, 2021
PyBullet CartPole and Quadrotor environments—with CasADi symbolic a priori dynamics—for learning-based control and reinforcement learning
PyBullet CartPole and Quadrotor environments—with CasADi symbolic a priori dynamics—for learning-based control and reinforcement learning

safe-control-gym Physics-based CartPole and Quadrotor Gym environments (using PyBullet) with symbolic a priori dynamics (using CasADi) for learning-ba

Dynamic Systems Lab 300 Dec 28, 2022
Safe Bayesian Optimization
Safe Bayesian Optimization

SafeOpt - Safe Bayesian Optimization This code implements an adapted version of the safe, Bayesian optimization algorithm, SafeOpt [1], [2]. It also p

Felix Berkenkamp 111 Dec 11, 2022
[NeurIPS 2021] Better Safe Than Sorry: Preventing Delusive Adversaries with Adversarial Training
[NeurIPS 2021] Better Safe Than Sorry: Preventing Delusive Adversaries with Adversarial Training

Better Safe Than Sorry: Preventing Delusive Adversaries with Adversarial Training Code for NeurIPS 2021 paper "Better Safe Than Sorry: Preventing Delu

Lue Tao 29 Sep 20, 2022
Infrastructure as Code (IaC) for a self-hosted version of Gnosis Safe on AWS
Infrastructure as Code (IaC) for a self-hosted version of Gnosis Safe on AWS

Welcome to Yearn Gnosis Safe! Setting up your local environment Infrastructure Deploying Gnosis Safe Prerequisites 1. Create infrastructure for secret

Numan 16 Jul 18, 2022
​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
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
Comments
  • How is the episode total cost tested during training?

    How is the episode total cost tested during training?

    Hello! I think CAP is a wonderful job but there are still some implementational details that confuse me. It seems that there are no additional testing/evaluating stage during policy training? Is this epoch_cost used as the testing metric? If so, why is the cost discounted while the reward isn't?

    opened by Zarzard 0
Owner
Undergraduate student at University of Melbourne, interested in Machine Learning
null
GitHub
Adaptive Attention Span for Reinforcement Learning

Adaptive Transformers in RL Official implementation of Adaptive Transformers in RL In this work we replicate several results from Stabilizing Transfor

null 100 Nov 15, 2022
Optimal Adaptive Allocation using Deep Reinforcement Learning in a Dose-Response Study

Optimal Adaptive Allocation using Deep Reinforcement Learning in a Dose-Response Study Supplementary Materials for Kentaro Matsuura, Junya Honda, Imad

Kentaro Matsuura 4 Nov 1, 2022
Keeping it safe - AI Based COVID-19 Tracker using Deep Learning and facial recognition

Keeping it safe - AI Based COVID-19 Tracker using Deep Learning and facial recognition

Vansh Wassan 15 Jun 17, 2021
Reinforcement-learning - Repository of the class assignment questions for the course on reinforcement learning

DSE 314/614: Reinforcement Learning This repository containing reinforcement lea

Manav Mishra 4 Apr 15, 2022
The implementation of the algorithm in the paper "Safe Deep Semi-Supervised Learning for Unseen-Class Unlabeled Data" published in ICML 2020.

DS3L This is the code for paper "Safe Deep Semi-Supervised Learning for Unseen-Class Unlabeled Data" published in ICML 2020. Setups The code is implem

Guolz 36 Oct 19, 2022
SafePicking: Learning Safe Object Extraction via Object-Level Mapping, ICRA 2022

SafePicking Learning Safe Object Extraction via Object-Level Mapping Kentaro Wad

Kentaro Wada 49 Oct 24, 2022
A pytorch reprelication of the model-based reinforcement learning algorithm MBPO

Overview This is a re-implementation of the model-based RL algorithm MBPO in pytorch as described in the following paper: When to Trust Your Model: Mo

Xingyu Lin 93 Jan 5, 2023
Model-based reinforcement learning in TensorFlow

Bellman Website | Twitter | Documentation (latest) What does Bellman do? Bellman is a package for model-based reinforcement learning (MBRL) in Python,

null 46 Nov 9, 2022
mbrl-lib is a toolbox for facilitating development of Model-Based Reinforcement Learning algorithms.

mbrl-lib is a toolbox for facilitating development of Model-Based Reinforcement Learning algorithms. It provides easily interchangeable modeling and planning components, and a set of utility functions that allow writing model-based RL algorithms with only a few lines of code.

Facebook Research 724 Jan 4, 2023
JAX code for the paper "Control-Oriented Model-Based Reinforcement Learning with Implicit Differentiation"

Optimal Model Design for Reinforcement Learning This repository contains JAX code for the paper Control-Oriented Model-Based Reinforcement Learning wi

Evgenii Nikishin 43 Sep 28, 2022