steveKapturowski / Tensorflow Rl
Licence: apache-2.0
Implementations of deep RL papers and random experimentation
Stars: β 176
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Tensorflow Rl
Deeprl Tensorflow2
π Simple implementations of various popular Deep Reinforcement Learning algorithms using TensorFlow2
Stars: β 319 (+81.25%)
Mutual labels: reinforcement-learning, dqn, a3c, trpo
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: β 222 (+26.14%)
Mutual labels: openai-gym, dqn, a3c, trpo
Pytorch Rl
Deep Reinforcement Learning with pytorch & visdom
Stars: β 745 (+323.3%)
Mutual labels: reinforcement-learning, dqn, a3c, trpo
Mushroom Rl
Python library for Reinforcement Learning.
Stars: β 442 (+151.14%)
Mutual labels: reinforcement-learning, dqn, openai-gym, trpo
Reinforcement Learning With Tensorflow
Simple Reinforcement learning tutorials, θ«η¦Python δΈζAIζε¦
Stars: β 6,948 (+3847.73%)
Mutual labels: reinforcement-learning, dqn, a3c
Ros2learn
ROS 2 enabled Machine Learning algorithms
Stars: β 119 (-32.39%)
Mutual labels: reinforcement-learning, dqn, trpo
Btgym
Scalable, event-driven, deep-learning-friendly backtesting library
Stars: β 765 (+334.66%)
Mutual labels: reinforcement-learning, openai-gym, a3c
Reinforcement learning
Reinforcement learning tutorials
Stars: β 82 (-53.41%)
Mutual labels: reinforcement-learning, dqn, a3c
Rl a3c pytorch
A3C LSTM Atari with Pytorch plus A3G design
Stars: β 482 (+173.86%)
Mutual labels: reinforcement-learning, openai-gym, a3c
Tensorlayer
Deep Learning and Reinforcement Learning Library for Scientists and Engineers π₯
Stars: β 6,796 (+3761.36%)
Mutual labels: reinforcement-learning, dqn, a3c
Ctc Executioner
Master Thesis: Limit order placement with Reinforcement Learning
Stars: β 112 (-36.36%)
Mutual labels: reinforcement-learning, dqn, openai-gym
Reinforcementlearning Atarigame
Pytorch LSTM RNN for reinforcement learning to play Atari games from OpenAI Universe. We also use Google Deep Mind's Asynchronous Advantage Actor-Critic (A3C) Algorithm. This is much superior and efficient than DQN and obsoletes it. Can play on many games
Stars: β 118 (-32.95%)
Mutual labels: reinforcement-learning, openai-gym, a3c
Hands On Reinforcement Learning With Python
Master Reinforcement and Deep Reinforcement Learning using OpenAI Gym and TensorFlow
Stars: β 640 (+263.64%)
Mutual labels: reinforcement-learning, openai-gym, trpo
Gym Anytrading
The most simple, flexible, and comprehensive OpenAI Gym trading environment (Approved by OpenAI Gym)
Stars: β 627 (+256.25%)
Mutual labels: reinforcement-learning, dqn, openai-gym
Minimalrl
Implementations of basic RL algorithms with minimal lines of codes! (pytorch based)
Stars: β 2,051 (+1065.34%)
Mutual labels: reinforcement-learning, dqn, a3c
Slm Lab
Modular Deep Reinforcement Learning framework in PyTorch. Companion library of the book "Foundations of Deep Reinforcement Learning".
Stars: β 904 (+413.64%)
Mutual labels: reinforcement-learning, dqn, a3c
Deep Reinforcement Learning With Pytorch
PyTorch implementation of DQN, AC, ACER, A2C, A3C, PG, DDPG, TRPO, PPO, SAC, TD3 and ....
Stars: β 1,345 (+664.2%)
Mutual labels: dqn, a3c, trpo
Openaigym
Solving OpenAI Gym problems.
Stars: β 98 (-44.32%)
Mutual labels: reinforcement-learning, dqn, openai-gym
Deep Rl Keras
Keras Implementation of popular Deep RL Algorithms (A3C, DDQN, DDPG, Dueling DDQN)
Stars: β 395 (+124.43%)
Mutual labels: reinforcement-learning, dqn, a3c
Cartpole
OpenAI's cartpole env solver.
Stars: β 107 (-39.2%)
Mutual labels: reinforcement-learning, dqn, openai-gym
Tensorflow-RL
Tensorflow based implementations of A3C, PGQ, TRPO, DQN+CTS, and CEM originally based on the A3C implementation from https://github.com/traai/async-deep-rl. I extensively refactored most of the code and beyond the new algorithms added several additional options including the a3c-lstm architecture, a fully-connected architecture to allow training on non-image-based gym environments, and support for continuous action spaces.
The code also includes some experimental ideas I'm toying with and I'm planning on adding the following implementations in the near future:
- High-Dimensional Continuous Control Using Generalized Advantage Estimation
- Q-Prop: Sample-Efficient Policy Gradient with An Off-Policy Critic
- Reinforcement Learning with Unsupervised Auxiliary Tasks
- FeUdal Networks for Hierarchical Reinforcement Learning*
- Prioritized Experience Replay
- Neural Episodic Control*
*currently in progress
Notes
- You can find a number of my evaluations for the A3C, TRPO, and DQN+CTS algorithms at https://gym.openai.com/users/steveKapturowski. As I'm working on lots of refactoring at the moment it's possible I could break things. Please open an issue if you discover any bugs.
- I'm in the process of swapping out most of the multiprocessing code in favour of distributed tensorflow which should simplify a lot of the training code and allow to distribute actor-learner processes across multiple machines.
- There's also an implementation of the A3C+ model from Unifying Count-Based Exploration and Intrinsic Motivation but I've been focusing on improvements to the DQN variant so this hasn't gotten much love
Running the code
First you'll need to install the cython extensions needed for the hog updates and CTS density model:
./setup.py install build_ext --inplace
To train an a3c agent on Pong run:
python main.py Pong-v0 --alg_type a3c -n 8
To evaluate a trained agent simply add the --test flag:
python main.py Pong-v0 --alg_type a3c -n 1 --test --restore_checkpoint
DQN+CTS after 80M agent steps using 16 actor-learner threads
A3C run on Pong-v0 with default parameters and frameskip sampled uniformly over 3-4
Requirements
- python 2.7
- tensorflow 1.2
- scikit-image
- Cython
- pyaml
- gym
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].