NovelD: A Simple yet Effective Exploration Criterion

Related tags

Deep Learning NovelD
Overview

NovelD: A Simple yet Effective Exploration Criterion

Intro

This is an implementation of the method proposed in

NovelD: A Simple yet Effective Exploration Criterion and BeBold: Exploration Beyond the Boundary of Explored Regions

Citation

If you use this code in your own work, please cite our paper:

@article{zhang2021noveld,
  title={NovelD: A Simple yet Effective Exploration Criterion},
  author={Zhang, Tianjun and Xu, Huazhe and Wang, Xiaolong and Wu, Yi and Keutzer, Kurt and Gonzalez, Joseph E and Tian, Yuandong},
  journal={Advances in Neural Information Processing Systems},
  volume={34},
  year={2021}
}

or

@article{zhang2020bebold,
  title={BeBold: Exploration Beyond the Boundary of Explored Regions},
  author={Zhang, Tianjun and Xu, Huazhe and Wang, Xiaolong and Wu, Yi and Keutzer, Kurt and Gonzalez, Joseph E and Tian, Yuandong},
  journal={arXiv preprint arXiv:2012.08621},
  year={2020}
}

Installation

# Install Instructions
conda create -n ride python=3.7
conda activate noveld 
git clone [email protected]:tianjunz/NovelD.git
cd NovelD
pip install -r requirements.txt

Train NovelD on MiniGrid

OMP_NUM_THREADS=1 python main.py --model bebold --env MiniGrid-ObstructedMaze-2Dlhb-v0 --total_frames 500000000 --intrinsic_reward_coef 0.05 --entropy_cost 0.0005

Acknowledgements

Our vanilla RL algorithm is based on RIDE.

License

This code is under the CC-BY-NC 4.0 (Attribution-NonCommercial 4.0 International) license.

You might also like...
An exploration of log domain "alternative floating point" for hardware ML/AI accelerators.

This repository contains the SystemVerilog RTL, C++, HLS (Intel FPGA OpenCL to wrap RTL code) and Python needed to reproduce the numerical results in

Facebook Research 373 Dec 31, 2022
RE3: State Entropy Maximization with Random Encoders for Efficient Exploration

State Entropy Maximization with Random Encoders for Efficient Exploration (RE3) (ICML 2021) Code for State Entropy Maximization with Random Encoders f

Younggyo Seo 47 Nov 29, 2022
Generative Exploration and Exploitation - This is an improved version of GENE.
Generative Exploration and Exploitation - This is an improved version of GENE.

GENE This is an improved version of GENE. In the original version, the states are generated from the decoder of VAE. We have to check whether the gere

null 33 Mar 23, 2022
Systemic Evolutionary Chemical Space Exploration for Drug Discovery
Systemic Evolutionary Chemical Space Exploration for Drug Discovery

SECSE SECSE: Systemic Evolutionary Chemical Space Explorer Chemical space exploration is a major task of the hit-finding process during the pursuit of

null 64 Dec 16, 2022
A repository with exploration into using transformers to predict DNA ↔ transcription factor binding

Transcription Factor binding predictions with Attention and Transformers A repository with exploration into using transformers to predict DNA ↔ transc

Phil Wang 62 Dec 20, 2022
Learning from Guided Play: A Scheduled Hierarchical Approach for Improving Exploration in Adversarial Imitation Learning Source Code
Learning from Guided Play: A Scheduled Hierarchical Approach for Improving Exploration in Adversarial Imitation Learning Source Code

Learning from Guided Play: A Scheduled Hierarchical Approach for Improving Exploration in Adversarial Imitation Learning Source Code

STARS Laboratory 8 Sep 14, 2022
Multi-robot collaborative exploration and mapping through Voronoi partition and DRL in unknown environment
Multi-robot collaborative exploration and mapping through Voronoi partition and DRL in unknown environment

Voronoi Multi_Robot Collaborate Exploration Introduction In the unknown environment, the cooperative exploration of multiple robots is completed by Vo

PeaceWord 6 Nov 22, 2022
A clear, concise, simple yet powerful and efficient API for deep learning.
A clear, concise, simple yet powerful and efficient API for deep learning.

The Gluon API Specification The Gluon API specification is an effort to improve speed, flexibility, and accessibility of deep learning technology for

Gluon API 2.3k Dec 17, 2022
SeqTR: A Simple yet Universal Network for Visual Grounding
SeqTR: A Simple yet Universal Network for Visual Grounding

SeqTR This is the official implementation of SeqTR: A Simple yet Universal Network for Visual Grounding, which simplifies and unifies the modelling fo

seanZhuh 76 Dec 24, 2022
Comments
  • MiniGrid results appear to be using the fully observable space as opposed to the partially observable one

    MiniGrid results appear to be using the fully observable space as opposed to the partially observable one

    First off, thanks for releasing the code. I ran into this paper not too long ago and found it pretty interesting.

    I was under the impression that the MiniGrid experiments in your NovelD paper you use the partial observation of the agent, but it appears that you are using the fully-observable one, per these lines:

    https://github.com/tianjunz/NovelD/blob/master/src/utils.py#L112-L114

    Can you clarify if this is true? A lot of users of MiniGrid assume that you use the partially observable view from the agent, so this seems like an important detail that needs to be mentioned...

    opened by vlawhern 0
  • Cannot reproduce result on ObstructedMaze-2Dlhb

    Cannot reproduce result on ObstructedMaze-2Dlhb

    Hi @tianjunz

    I ran your codes with the same command you suggested as OMP_NUM_THREADS=1 python main.py --model bebold --env MiniGrid-ObstructedMaze-2Dlhb-v0 --total_frames 500000000 --intrinsic_reward_coef 0.05 --entropy_cost 0.0005

    However, the obtained "mean episode return" is still 0 even after 60M frames, which is different from that in Fig.4 in the paper (NovelD). my log: logs.csv Could you check it or share your result (log)?

    FYI, MultiRoom and KeyCorridor tasks seem to be reproduced. I used the following versions: pytorch(1.10.0), gym(0.15.4), gym_minigrid(1.0.2).

    Thanks, Sungwoong.

    opened by sungwoong 2
Owner
null
GitHub
A Pytorch implementation of CVPR 2021 paper "RSG: A Simple but Effective Module for Learning Imbalanced Datasets"

RSG: A Simple but Effective Module for Learning Imbalanced Datasets (CVPR 2021) A Pytorch implementation of our CVPR 2021 paper "RSG: A Simple but Eff

null 120 Dec 12, 2022
Simple and Effective Few-Shot Named Entity Recognition with Structured Nearest Neighbor Learning

structshot Code and data for paper "Simple and Effective Few-Shot Named Entity Recognition with Structured Nearest Neighbor Learning", Yi Yang and Arz

ASAPP Research 47 Dec 27, 2022
Official code of ICCV2021 paper "Residual Attention: A Simple but Effective Method for Multi-Label Recognition"

CSRA This is the official code of ICCV 2021 paper: Residual Attention: A Simple But Effective Method for Multi-Label Recoginition Demo, Train and Vali

null 163 Dec 22, 2022
A pytorch implementation of the ACL2019 paper "Simple and Effective Text Matching with Richer Alignment Features".

RE2 This is a pytorch implementation of the ACL 2019 paper "Simple and Effective Text Matching with Richer Alignment Features". The original Tensorflo

null 287 Dec 21, 2022
[SIGIR22] Official PyTorch implementation for "CORE: Simple and Effective Session-based Recommendation within Consistent Representation Space".

CORE This is the official PyTorch implementation for the paper: Yupeng Hou, Binbin Hu, Zhiqiang Zhang, Wayne Xin Zhao. CORE: Simple and Effective Sess

RUCAIBox 26 Dec 19, 2022
A mini library for Policy Gradients with Parameter-based Exploration, with reference implementation of the ClipUp optimizer from NNAISENSE.

PGPElib A mini library for Policy Gradients with Parameter-based Exploration [1] and friends. This library serves as a clean re-implementation of the

NNAISENSE 56 Jan 1, 2023
Code for the paper Language as a Cognitive Tool to Imagine Goals in Curiosity Driven Exploration

IMAGINE: Language as a Cognitive Tool to Imagine Goals in Curiosity Driven Exploration This repo contains the code base of the paper Language as a Cog

Flowers Team 26 Dec 22, 2022
Exploration-Exploitation Dilemma Solving Methods

Exploration-Exploitation Dilemma Solving Methods Medium article for this repo - HERE In ths repo I implemented two techniques for tackling mentioned t

Aman Mishra 6 Jan 25, 2022
[Preprint] "Chasing Sparsity in Vision Transformers: An End-to-End Exploration" by Tianlong Chen, Yu Cheng, Zhe Gan, Lu Yuan, Lei Zhang, Zhangyang Wang

Chasing Sparsity in Vision Transformers: An End-to-End Exploration Codes for [Preprint] Chasing Sparsity in Vision Transformers: An End-to-End Explora

VITA 64 Dec 8, 2022
PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models

PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models Code accompanying CVPR'20 paper of the same title. Paper lin

Alex Damian 7k Dec 30, 2022