rl topic

Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.

google

Reinforcement learning theory book about foundations of deep RL algorithms with proofs.

FortsAndMills

ELF: a platform for game research with AlphaGoZero/AlphaZero reimplementation

pytorch

[ICML 2017] TensorFlow code for Curiosity-driven Exploration for Deep Reinforcement Learning

pathak22

A collection of 100+ pre-trained RL agents using Stable Baselines, training and hyperparameter optimization included.

araffin

A training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included.

DLR-RM

SEED RL: Scalable and Efficient Deep-RL with Accelerated Central Inference. Implements IMPALA and R2D2 algorithms in TF2 with SEED's architecture.

google-research

Python library for Reinforcement Learning.

MushroomRL

Hearthstone simulator using C++ with some reinforcement learning

utilForever

[NeurIPS'21 Outstanding Paper] Library for reliable evaluation on RL and ML benchmarks, even with only a handful of seeds.

google-research