All Projects → ShangtongZhang → Deeprl

ShangtongZhang / Deeprl

Licence: mit
Modularized Implementation of Deep RL Algorithms in PyTorch

Programming Languages

python
139335 projects - #7 most used programming language
Dockerfile
14818 projects
shell
77523 projects

Projects that are alternatives of or similar to Deeprl

Deep-Reinforcement-Learning-With-Python
Master classic RL, deep RL, distributional RL, inverse RL, and more using OpenAI Gym and TensorFlow with extensive Math
Stars: ✭ 222 (-91.59%)
Mutual labels:  deep-reinforcement-learning, dqn, ddpg, double-dqn, ppo, a2c, td3
Rainy
☔ Deep RL agents with PyTorch☔
Stars: ✭ 39 (-98.52%)
Mutual labels:  deep-reinforcement-learning, dqn, ddpg, ppo, a2c, option-critic, td3
ReinforcementLearningZoo.jl
juliareinforcementlearning.org/
Stars: ✭ 46 (-98.26%)
Mutual labels:  rainbow, dqn, ddpg, ppo, a2c, td3
Deep-Reinforcement-Learning-Notebooks
This Repository contains a series of google colab notebooks which I created to help people dive into deep reinforcement learning.This notebooks contain both theory and implementation of different algorithms.
Stars: ✭ 15 (-99.43%)
Mutual labels:  deep-reinforcement-learning, rainbow, dqn, ppo, a2c, prioritized-experience-replay
Tianshou
An elegant PyTorch deep reinforcement learning library.
Stars: ✭ 4,109 (+55.64%)
Mutual labels:  dqn, ppo, ddpg, double-dqn, a2c, td3
Deep-rl-mxnet
Mxnet implementation of Deep Reinforcement Learning papers, such as DQN, PG, DDPG, PPO
Stars: ✭ 26 (-99.02%)
Mutual labels:  deep-reinforcement-learning, dqn, ddpg, a2c, td3
ElegantRL
Scalable and Elastic Deep Reinforcement Learning Using PyTorch. Please star. 🔥
Stars: ✭ 2,074 (-21.44%)
Mutual labels:  dqn, ddpg, ppo, a2c, td3
Minimalrl
Implementations of basic RL algorithms with minimal lines of codes! (pytorch based)
Stars: ✭ 2,051 (-22.31%)
Mutual labels:  deep-reinforcement-learning, dqn, ppo, ddpg, a2c
Reinforcement Learning Algorithms
This repository contains most of pytorch implementation based classic deep reinforcement learning algorithms, including - DQN, DDQN, Dueling Network, DDPG, SAC, A2C, PPO, TRPO. (More algorithms are still in progress)
Stars: ✭ 426 (-83.86%)
Mutual labels:  deep-reinforcement-learning, dqn, ppo, ddpg
Easy Rl
强化学习中文教程,在线阅读地址:https://datawhalechina.github.io/easy-rl/
Stars: ✭ 3,004 (+13.79%)
Mutual labels:  deep-reinforcement-learning, dqn, ppo, ddpg
Machine Learning Is All You Need
🔥🌟《Machine Learning 格物志》: ML + DL + RL basic codes and notes by sklearn, PyTorch, TensorFlow, Keras & the most important, from scratch!💪 This repository is ALL You Need!
Stars: ✭ 173 (-93.45%)
Mutual labels:  deep-reinforcement-learning, dqn, ppo, ddpg
Autonomous Learning Library
A PyTorch library for building deep reinforcement learning agents.
Stars: ✭ 425 (-83.9%)
Mutual labels:  deep-reinforcement-learning, dqn, ppo, ddpg
Paddle-RLBooks
Paddle-RLBooks is a reinforcement learning code study guide based on pure PaddlePaddle.
Stars: ✭ 113 (-95.72%)
Mutual labels:  dqn, ddpg, double-dqn, td3
model-free-algorithms
TD3, SAC, IQN, Rainbow, PPO, Ape-X and etc. in TF1.x
Stars: ✭ 56 (-97.88%)
Mutual labels:  rainbow, ddpg, ppo, td3
rl implementations
No description or website provided.
Stars: ✭ 40 (-98.48%)
Mutual labels:  deep-reinforcement-learning, dqn, ddpg, a2c
Deep Reinforcement Learning
Repo for the Deep Reinforcement Learning Nanodegree program
Stars: ✭ 4,012 (+51.97%)
Mutual labels:  deep-reinforcement-learning, dqn, ppo, ddpg
Deep RL with pytorch
A pytorch tutorial for DRL(Deep Reinforcement Learning)
Stars: ✭ 160 (-93.94%)
Mutual labels:  deep-reinforcement-learning, dqn, ppo, a2c
Deeprl Tensorflow2
🐋 Simple implementations of various popular Deep Reinforcement Learning algorithms using TensorFlow2
Stars: ✭ 319 (-87.92%)
Mutual labels:  deep-reinforcement-learning, dqn, ppo, ddpg
Reinforcement Learning
Learn Deep Reinforcement Learning in 60 days! Lectures & Code in Python. Reinforcement Learning + Deep Learning
Stars: ✭ 3,329 (+26.1%)
Mutual labels:  deep-reinforcement-learning, dqn, ppo, a2c
Reinforcement Learning With Tensorflow
Simple Reinforcement learning tutorials, 莫烦Python 中文AI教学
Stars: ✭ 6,948 (+163.18%)
Mutual labels:  dqn, ppo, ddpg, double-dqn

DeepRL

If you have any question or want to report a bug, please open an issue instead of emailing me directly.

Modularized implementation of popular deep RL algorithms in PyTorch.
Easy switch between toy tasks and challenging games.

Implemented algorithms:

  • (Double/Dueling/Prioritized) Deep Q-Learning (DQN)
  • Categorical DQN (C51)
  • Quantile Regression DQN (QR-DQN)
  • (Continuous/Discrete) Synchronous Advantage Actor Critic (A2C)
  • Synchronous N-Step Q-Learning (N-Step DQN)
  • Deep Deterministic Policy Gradient (DDPG)
  • Proximal Policy Optimization (PPO)
  • The Option-Critic Architecture (OC)
  • Twined Delayed DDPG (TD3)
  • DifferentialGQ/MVPI/ReverseRL/COF-PAC/GradientDICE/Bi-Res-DDPG/DAC/Geoff-PAC/QUOTA/ACE

The DQN agent, as well as C51 and QR-DQN, has an asynchronous actor for data generation and an asynchronous replay buffer for transferring data to GPU. Using 1 RTX 2080 Ti and 3 threads, the DQN agent runs for 10M steps (40M frames, 2.5M gradient updates) for Breakout within 6 hours.

Dependency

  • PyTorch v1.5.1
  • See Dockerfile and requirements.txt for more details

Usage

examples.py contains examples for all the implemented algorithms.
Dockerfile contains the environment for generating the curves below.
Please use this bibtex if you want to cite this repo

@misc{deeprl,
  author = {Zhang, Shangtong},
  title = {Modularized Implementation of Deep RL Algorithms in PyTorch},
  year = {2018},
  publisher = {GitHub},
  journal = {GitHub Repository},
  howpublished = {\url{https://github.com/ShangtongZhang/DeepRL}},
}

Curves (commit 9e811e)

BreakoutNoFrameskip-v4 (1 run)

Loading...

Mujoco

  • DDPG/TD3 evaluation performance. Loading... (5 runs, mean + standard error)

  • PPO online performance. Loading... (5 runs, mean + standard error, smoothed by a window of size 10)

References

Code of My Papers

They are located in other branches of this repo and seem to be good examples for using this codebase.

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].