PyTorch implementation of Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO), Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation (ACKTR) and Generative Adversarial Imitation Learning (GAIL).

Overview

pytorch-a2c-ppo-acktr

Update (April 12th, 2021)

PPO is great, but Soft Actor Critic can be better for many continuous control tasks. Please check out my new RL repository in jax.

Please use hyper parameters from this readme. With other hyper parameters things might not work (it's RL after all)!

This is a PyTorch implementation of

  • Advantage Actor Critic (A2C), a synchronous deterministic version of A3C
  • Proximal Policy Optimization PPO
  • Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation ACKTR
  • Generative Adversarial Imitation Learning GAIL

Also see the OpenAI posts: A2C/ACKTR and PPO for more information.

This implementation is inspired by the OpenAI baselines for A2C, ACKTR and PPO. It uses the same hyper parameters and the model since they were well tuned for Atari games.

Please use this bibtex if you want to cite this repository in your publications:

@misc{pytorchrl,
  author = {Kostrikov, Ilya},
  title = {PyTorch Implementations of Reinforcement Learning Algorithms},
  year = {2018},
  publisher = {GitHub},
  journal = {GitHub repository},
  howpublished = {\url{https://github.com/ikostrikov/pytorch-a2c-ppo-acktr-gail}},
}

Supported (and tested) environments (via OpenAI Gym)

I highly recommend PyBullet as a free open source alternative to MuJoCo for continuous control tasks.

All environments are operated using exactly the same Gym interface. See their documentations for a comprehensive list.

To use the DeepMind Control Suite environments, set the flag --env-name dm.<domain_name>.<task_name>, where domain_name and task_name are the name of a domain (e.g. hopper) and a task within that domain (e.g. stand) from the DeepMind Control Suite. Refer to their repo and their tech report for a full list of available domains and tasks. Other than setting the task, the API for interacting with the environment is exactly the same as for all the Gym environments thanks to dm_control2gym.

Requirements

In order to install requirements, follow:

# PyTorch
conda install pytorch torchvision -c soumith

# Other requirements
pip install -r requirements.txt

Contributions

Contributions are very welcome. If you know how to make this code better, please open an issue. If you want to submit a pull request, please open an issue first. Also see a todo list below.

Also I'm searching for volunteers to run all experiments on Atari and MuJoCo (with multiple random seeds).

Disclaimer

It's extremely difficult to reproduce results for Reinforcement Learning methods. See "Deep Reinforcement Learning that Matters" for more information. I tried to reproduce OpenAI results as closely as possible. However, majors differences in performance can be caused even by minor differences in TensorFlow and PyTorch libraries.

TODO

  • Improve this README file. Rearrange images.
  • Improve performance of KFAC, see kfac.py for more information
  • Run evaluation for all games and algorithms

Visualization

In order to visualize the results use visualize.ipynb.

Training

Atari

A2C

python main.py --env-name "PongNoFrameskip-v4"

PPO

python main.py --env-name "PongNoFrameskip-v4" --algo ppo --use-gae --lr 2.5e-4 --clip-param 0.1 --value-loss-coef 0.5 --num-processes 8 --num-steps 128 --num-mini-batch 4 --log-interval 1 --use-linear-lr-decay --entropy-coef 0.01

ACKTR

python main.py --env-name "PongNoFrameskip-v4" --algo acktr --num-processes 32 --num-steps 20

MuJoCo

Please always try to use --use-proper-time-limits flag. It properly handles partial trajectories (see https://github.com/sfujim/TD3/blob/master/main.py#L123).

A2C

python main.py --env-name "Reacher-v2" --num-env-steps 1000000

PPO

python main.py --env-name "Reacher-v2" --algo ppo --use-gae --log-interval 1 --num-steps 2048 --num-processes 1 --lr 3e-4 --entropy-coef 0 --value-loss-coef 0.5 --ppo-epoch 10 --num-mini-batch 32 --gamma 0.99 --gae-lambda 0.95 --num-env-steps 1000000 --use-linear-lr-decay --use-proper-time-limits

ACKTR

ACKTR requires some modifications to be made specifically for MuJoCo. But at the moment, I want to keep this code as unified as possible. Thus, I'm going for better ways to integrate it into the codebase.

Enjoy

Load a pretrained model from my Google Drive.

Also pretrained models for other games are available on request. Send me an email or create an issue, and I will upload it.

Disclaimer: I might have used different hyper-parameters to train these models.

Atari

python enjoy.py --load-dir trained_models/a2c --env-name "PongNoFrameskip-v4"

MuJoCo

python enjoy.py --load-dir trained_models/ppo --env-name "Reacher-v2"

Results

A2C

BreakoutNoFrameskip-v4

SeaquestNoFrameskip-v4

QbertNoFrameskip-v4

beamriderNoFrameskip-v4

PPO

BreakoutNoFrameskip-v4

SeaquestNoFrameskip-v4

QbertNoFrameskip-v4

beamriderNoFrameskip-v4

ACKTR

BreakoutNoFrameskip-v4

SeaquestNoFrameskip-v4

QbertNoFrameskip-v4

beamriderNoFrameskip-v4

Owner
Ilya Kostrikov
Post doc
Ilya Kostrikov
Code for "Sparse Steerable Convolutions: An Efficient Learning of SE(3)-Equivariant Features for Estimation and Tracking of Object Poses in 3D Space"

Sparse Steerable Convolution (SS-Conv) Code for "Sparse Steerable Convolutions: An Efficient Learning of SE(3)-Equivariant Features for Estimation and

25 Dec 21, 2022
Open source simulator for autonomous vehicles built on Unreal Engine / Unity, from Microsoft AI & Research

Welcome to AirSim AirSim is a simulator for drones, cars and more, built on Unreal Engine (we now also have an experimental Unity release). It is open

Microsoft 13.8k Jan 05, 2023
Our CIKM21 Paper "Incorporating Query Reformulating Behavior into Web Search Evaluation"

Reformulation-Aware-Metrics Introduction This codebase contains source-code of the Python-based implementation of our CIKM 2021 paper. Chen, Jia, et a

xuanyuan14 5 Mar 05, 2022
A PyTorch implementation of the WaveGlow: A Flow-based Generative Network for Speech Synthesis

WaveGlow A PyTorch implementation of the WaveGlow: A Flow-based Generative Network for Speech Synthesis Quick Start: Install requirements: pip install

Yuchao Zhang 204 Jul 14, 2022
Genpass - A Passwors Generator App With Python3

Genpass Welcom again into another python3 App this is simply an Passwors Generat

Mal4D 1 Jan 09, 2022
Visyerres sgdf woob - Modules Woob pour l'intranet et autres sites Scouts et Guides de France

Vis'Yerres SGDF - Modules Woob Vous avez le sentiment que l'intranet des Scouts

Thomas Touhey (pas un pseudonyme) 3 Dec 24, 2022
Learning View Priors for Single-view 3D Reconstruction (CVPR 2019)

Learning View Priors for Single-view 3D Reconstruction (CVPR 2019) This is code for a paper Learning View Priors for Single-view 3D Reconstruction by

Hiroharu Kato 38 Aug 17, 2022
A collection of inference modules for fastai2

fastinference A collection of inference modules for fastai including inference speedup and interpretability Install pip install fastinference There ar

Zachary Mueller 83 Oct 10, 2022
MVFNet: Multi-View Fusion Network for Efficient Video Recognition (AAAI 2021)

MVFNet: Multi-View Fusion Network for Efficient Video Recognition (AAAI 2021) Overview We release the code of the MVFNet (Multi-View Fusion Network).

2 Jan 29, 2022
Code to produce syntactic representations that can be used to study syntax processing in the human brain

Can fMRI reveal the representation of syntactic structure in the brain? The code base for our paper on understanding syntactic representations in the

Aniketh Janardhan Reddy 4 Dec 18, 2022
Reference models and tools for Cloud TPUs.

Cloud TPUs This repository is a collection of reference models and tools used with Cloud TPUs. The fastest way to get started training a model on a Cl

5k Jan 05, 2023
Learning Temporal Consistency for Low Light Video Enhancement from Single Images (CVPR2021)

StableLLVE This is a Pytorch implementation of "Learning Temporal Consistency for Low Light Video Enhancement from Single Images" in CVPR 2021, by Fan

99 Dec 19, 2022
Official Implementation of VAT

Semantic correspondence Few-shot segmentation Cost Aggregation Is All You Need for Few-Shot Segmentation For more information, check out project [Proj

Hamacojr 114 Dec 27, 2022
Python package to generate image embeddings with CLIP without PyTorch/TensorFlow

imgbeddings A Python package to generate embedding vectors from images, using OpenAI's robust CLIP model via Hugging Face transformers. These image em

Max Woolf 81 Jan 04, 2023
Deep Learning Tutorial for Kaggle Ultrasound Nerve Segmentation competition, using Keras

Deep Learning Tutorial for Kaggle Ultrasound Nerve Segmentation competition, using Keras This tutorial shows how to use Keras library to build deep ne

Marko Jocić 922 Dec 19, 2022
PyTorch and Tensorflow functional model definitions

functional-zoo Model definitions and pretrained weights for PyTorch and Tensorflow PyTorch, unlike lua torch, has autograd in it's core, so using modu

Sergey Zagoruyko 590 Dec 22, 2022
HyperDict - Self linked dictionary in Python

Hyper Dictionary Advanced python dictionary(hash-table), which can link it-self

8 Feb 06, 2022
Code for "Localization with Sampling-Argmax", NeurIPS 2021

Localization with Sampling-Argmax [Paper] [arXiv] [Project Page] Localization with Sampling-Argmax Jiefeng Li, Tong Chen, Ruiqi Shi, Yujing Lou, Yong-

JeffLi 71 Dec 17, 2022
SoGCN: Second-Order Graph Convolutional Networks

SoGCN: Second-Order Graph Convolutional Networks This is the authors' implementation of paper "SoGCN: Second-Order Graph Convolutional Networks" in Py

Yuehao 7 Aug 16, 2022
Breaching - Breaching privacy in federated learning scenarios for vision and text

Breaching - A Framework for Attacks against Privacy in Federated Learning This P

Jonas Geiping 139 Jan 03, 2023