GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → navneet-nmk → Pytorch Rl

navneet-nmk / Pytorch Rl

This repository contains model-free deep reinforcement learning algorithms implemented in Pytorch

Programming Languages

python
139335 projects - #7 most used programming language

Labels

deep-learningpytorchreinforcement-learningganroboticsgenerative-adversarial-networkdeep-reinforcement-learningdqnopenai-gymvaevariational-autoencodergympolicy-gradientddpgmujoco

Projects that are alternatives of or similar to Pytorch Rl

Mushroom Rl
Python library for Reinforcement Learning.
Stars: ✭ 442 (+12.18%)
Mutual labels:  reinforcement-learning, deep-reinforcement-learning, dqn, openai-gym, ddpg, mujoco
Deep Reinforcement Learning
Repo for the Deep Reinforcement Learning Nanodegree program
Stars: ✭ 4,012 (+918.27%)
Mutual labels:  reinforcement-learning, deep-reinforcement-learning, dqn, openai-gym, ddpg
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 (-43.65%)
Mutual labels:  deep-reinforcement-learning, openai-gym, dqn, policy-gradient, ddpg
Deterministic Gail Pytorch
PyTorch implementation of Deterministic Generative Adversarial Imitation Learning (GAIL) for Off Policy learning
Stars: ✭ 44 (-88.83%)
Mutual labels:  gym, reinforcement-learning, generative-adversarial-network, deep-reinforcement-learning, openai-gym
Lagom
lagom: A PyTorch infrastructure for rapid prototyping of reinforcement learning algorithms.
Stars: ✭ 364 (-7.61%)
Mutual labels:  reinforcement-learning, deep-reinforcement-learning, policy-gradient, ddpg, mujoco
Torchrl
Pytorch Implementation of Reinforcement Learning Algorithms ( Soft Actor Critic(SAC)/ DDPG / TD3 /DQN / A2C/ PPO / TRPO)
Stars: ✭ 90 (-77.16%)
Mutual labels:  gym, reinforcement-learning, dqn, ddpg, mujoco
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 (+662.44%)
Mutual labels:  reinforcement-learning, deep-reinforcement-learning, dqn, policy-gradient, ddpg
Deep Rl Keras
Keras Implementation of popular Deep RL Algorithms (A3C, DDQN, DDPG, Dueling DDQN)
Stars: ✭ 395 (+0.25%)
Mutual labels:  gym, reinforcement-learning, dqn, policy-gradient, ddpg
Rl algorithms
Structural implementation of RL key algorithms
Stars: ✭ 352 (-10.66%)
Mutual labels:  gym, reinforcement-learning, dqn, policy-gradient
rl implementations
No description or website provided.
Stars: ✭ 40 (-89.85%)
Mutual labels:  deep-reinforcement-learning, dqn, policy-gradient, ddpg
Drq
DrQ: Data regularized Q
Stars: ✭ 268 (-31.98%)
Mutual labels:  gym, reinforcement-learning, deep-reinforcement-learning, mujoco
Gym Gazebo2
gym-gazebo2 is a toolkit for developing and comparing reinforcement learning algorithms using ROS 2 and Gazebo
Stars: ✭ 257 (-34.77%)
Mutual labels:  gym, robotics, reinforcement-learning, deep-reinforcement-learning
Rl Book
Source codes for the book "Reinforcement Learning: Theory and Python Implementation"
Stars: ✭ 464 (+17.77%)
Mutual labels:  gym, reinforcement-learning, deep-reinforcement-learning, openai-gym
Pytorch sac ae
PyTorch implementation of Soft Actor-Critic + Autoencoder(SAC+AE)
Stars: ✭ 94 (-76.14%)
Mutual labels:  gym, reinforcement-learning, deep-reinforcement-learning, mujoco
Pytorch sac
PyTorch implementation of Soft Actor-Critic (SAC)
Stars: ✭ 174 (-55.84%)
Mutual labels:  gym, reinforcement-learning, deep-reinforcement-learning, mujoco
Openai lab
An experimentation framework for Reinforcement Learning using OpenAI Gym, Tensorflow, and Keras.
Stars: ✭ 313 (-20.56%)
Mutual labels:  reinforcement-learning, deep-reinforcement-learning, policy-gradient, ddpg
Pytorch-RL-CPP
A Repository with C++ implementations of Reinforcement Learning Algorithms (Pytorch)
Stars: ✭ 73 (-81.47%)
Mutual labels:  openai-gym, gym, vae, mujoco
Deeprl Tensorflow2
🐋 Simple implementations of various popular Deep Reinforcement Learning algorithms using TensorFlow2
Stars: ✭ 319 (-19.04%)
Mutual labels:  reinforcement-learning, deep-reinforcement-learning, dqn, ddpg
Reinforcement Learning
Minimal and Clean Reinforcement Learning Examples
Stars: ✭ 2,863 (+626.65%)
Mutual labels:  reinforcement-learning, deep-reinforcement-learning, dqn, policy-gradient
Deep-Reinforcement-Learning-CS285-Pytorch
Solutions of assignments of Deep Reinforcement Learning course presented by the University of California, Berkeley (CS285) in Pytorch framework
Stars: ✭ 104 (-73.6%)
Mutual labels:  deep-reinforcement-learning, openai-gym, policy-gradient, mujoco
View All Similar Projects ➔

Deep Reinforcement Learning in Pytorch

This repository contains all standard model-free and model-based(coming) RL algorithms in Pytorch. (May also contain some research ideas I am working on currently)

For C++ version of Pytorch-RL : Pytorch-RL-CPP

What is it?

pytorch-rl implements some state-of-the art deep reinforcement learning algorithms in Pytorch, especially those concerned with continuous action spaces. You can train your algorithm efficiently either on CPU or GPU. Furthermore, pytorch-rl works with OpenAI Gym out of the box. This means that evaluating and playing around with different algorithms is easy. Of course you can extend pytorch-rl according to your own needs. TL:DR : pytorch-rl makes it really easy to run state-of-the-art deep reinforcement learning algorithms.

Installation

Install Pytorch-rl from Pypi (recommended):

pip install pytorch-policy

Dependencies

  1. Pytorch
  2. Gym (OpenAI)
  3. mujoco-py (For the physics simulation and the robotics env in gym)
  4. Pybullet (Coming Soon)
  5. MPI (Only supported with mpi backend Pytorch installation)
  6. Tensorboardx (https://github.com/lanpa/tensorboardX)

RL algorithms

  1. DQN (with Double Q learning)
  2. DDPG
  3. DDPG with HER (For the OpenAI Fetch Environments)
  4. Heirarchical Reinforcement Learning
  5. Prioritized Experience Replay + DDPG
  6. DDPG with Prioritized Hindsight experience replay (Research)
  7. Neural Map with A3C (Coming Soon)
  8. Rainbow DQN (Coming Soon)
  9. PPO (https://github.com/ikostrikov/pytorch-a2c-ppo-acktr)
  10. HER with self attention for goal substitution (Research)
  11. A3C (Coming Soon)
  12. ACER (Coming Soon)
  13. DARLA
  14. TDM
  15. World Models
  16. Soft Actor-Critic
  17. Empowerment driven Exploration (Tensorflow implementation : https://github.com/navneet-nmk/Empowerment-driven-Exploration)

Environments

  1. Breakout
  2. Pong (coming soon)
  3. Hand Manipulation Robotic Task
  4. Fetch-Reach Robotic Task
  5. Hand-Reach Robotic Task
  6. Block Manipulation Robotic Task
  7. Montezuma's Revenge (Current Research)
  8. Pitfall
  9. Gravitar
  10. CarRacing
  11. Super Mario Bros (Follow instructions to install gym-retro https://github.com/openai/retro)
  12. OpenSim Prosthetics Nips Challenge (https://www.crowdai.org/challenges/nips-2018-ai-for-prosthetics-challenge)

Environment Modelling (For exploration and domain adaptation)

Multiple GAN training tricks have been used because of the instability in training the generators and discriminators. Please refer to https://github.com/soumith/ganhacks for more information.

Even after using the tricks, it was really hard to train a GAN to convergence. However, after using Spectral Normalization (https://arxiv.org/abs/1802.05957) the infogan was trained to convergence.

For image to image translation tasks with GANs and for VAEs in general, training with Skip Connection really helps the training.

  1. beta-VAE
  2. InfoGAN
  3. CVAE-GAN
  4. Flow based generative models (Research)
  5. SAGAN
  6. Sequential Attend, Infer, Repeat
  7. Curiosity driven exploration
  8. Parameter Space Noise for Exploration
  9. Noisy Network

References

  1. Playing Atari with Deep Reinforcement Learning, Mnih et al., 2013
  2. Human-level control through deep reinforcement learning, Mnih et al., 2015
  3. Deep Reinforcement Learning with Double Q-learning, van Hasselt et al., 2015
  4. Continuous control with deep reinforcement learning, Lillicrap et al., 2015
  5. CVAE-GAN: Fine-Grained Image Generation through Asymmetric Training, Bao et al., 2017
  6. beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework, Higgins et al., 2017
  7. Hindsight Experience Replay, Andrychowicz et al., 2017
  8. InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets, Chen et al., 2016
  9. World Models, Ha et al., 2018
  10. Spectral Normalization for Generative Adversarial Networks, Miyato et al., 2018
  11. Self-Attention Generative Adversarial Networks, Zhang et al., 2018
  12. Curiosity-driven Exploration by Self-supervised Prediction, Pathak et al., 2017
  13. Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor, Haarnoja et al., 2018
  14. Parameter Space Noise for Exploration, Plappert et al., 2018
  15. Noisy Network for Exploration, Fortunato et al., 2018
  16. Proximal Policy Optimization Algorithms, Schulman et al., 2017
  17. Unsupervised Real-Time Control through Variational Empowerment, Karl et al., 2017
  18. Mutual Information Neural Estimation, Belghazi et al., 2018
  19. Empowerment-driven Exploration using Mutual Information Estimation, Kumar et al., 2018
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].