Reinforcement Learning implementations and research prototyping in TensorFlow
RLTF is a research framework that provides high-quality implementations of common Reinforcement Learning algorithms. It also allows fast-prototyping and benchmarking of new methods.
Status: This work is under active development (breaking changes might occur).
Algorithm | Model | Agent |
---|---|---|
DQN | DQN | AgentDQN |
Double DQN | DDQN | AgentDQN |
Dueling DQN | next | next |
Prioritized Experience Replay | next | next |
C51 | C51 | AgentDQN |
QR-DQN | QRDQN | AgentDQN |
Bootstrapped DQN | BstrapDQN | AgentDQN |
Bootstrapped UCB | DQN_UCB | AgentDQN |
DQN Ensemble | DQN_Ensemble | AgentDQN |
BDQN | BDQN | AgentBDQN |
DQN-IDS | DQN-IDS | AgentDQN |
C51-IDS | C51-IDS | AgentDQN |
DDPG | DDPG | AgentDDPG |
REINFORCE | REINFORCE | AgentPG |
PPO | PPO | AgentPPO |
TRPO | TRPO | AgentTRPO |
Coming additions:
Implemented models are able to achieve comparable results to the ones reported in the corresponding papers. With tiny exceptions, all implementations should be equivalent to the ones described in the original papers.
Implementations known to misbehave:
The goal of this framework is to provide stable implementations of standard RL algorithms and simultaneously enable fast prototyping of new methods. Some important features include:
git clone https://github.com/nikonikolov/rltf.git
pip package coming soon
For brief documentation see docs/.
If you use this repository for you research, please cite:
@misc{rltf,
author = {Nikolay Nikolov},
title = {RLTF: Reinforcement Learning in TensorFlow},
year = {2018},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\url{https://github.com/nikonikolov/rltf}},
}