| google/dopamine |
10,248 |
|
31 |
5 |
over 2 years ago |
44 |
September 21, 2022 |
100 |
apache-2.0 |
Jupyter Notebook |
| Dopamine is a research framework for fast prototyping of reinforcement learning algorithms. |
| thu-ml/tianshou |
7,125 |
|
0 |
10 |
about 2 years ago |
33 |
August 22, 2023 |
97 |
mit |
Python |
| An elegant PyTorch deep reinforcement learning library. |
| facebookresearch/ReAgent |
3,502 |
|
0 |
0 |
about 2 years ago |
2 |
May 27, 2020 |
86 |
bsd-3-clause |
Python |
| A platform for Reasoning systems (Reinforcement Learning, Contextual Bandits, etc.) |
| tensorflow/agents |
2,658 |
|
0 |
5 |
over 2 years ago |
49 |
October 03, 2023 |
184 |
apache-2.0 |
Python |
| TF-Agents: A reliable, scalable and easy to use TensorFlow library for Contextual Bandits and Reinforcement Learning. |
| higgsfield/RL-Adventure |
2,450 |
|
0 |
0 |
over 4 years ago |
0 |
|
16 |
|
Jupyter Notebook |
| Pytorch Implementation of DQN / DDQN / Prioritized replay/ noisy networks/ distributional values/ Rainbow/ hierarchical RL |
| seungeunrho/minimalRL |
2,417 |
|
0 |
0 |
almost 3 years ago |
0 |
|
21 |
mit |
Python |
| Implementations of basic RL algorithms with minimal lines of codes! (pytorch based) |
| MushroomRL/mushroom-rl |
746 |
|
0 |
4 |
about 2 years ago |
20 |
October 30, 2023 |
5 |
mit |
Python |
| Python library for Reinforcement Learning. |
| Denys88/rl_games |
603 |
|
0 |
1 |
over 2 years ago |
15 |
September 28, 2023 |
25 |
mit |
Jupyter Notebook |
| RL implementations |
| kingyuluk/FlappyBird |
555 |
|
0 |
0 |
over 3 years ago |
0 |
|
2 |
mit |
Java |
| 基于Java基础类库编写的Flappy Bird |
| google-research/batch_rl |
443 |
|
0 |
0 |
almost 3 years ago |
0 |
|
9 |
apache-2.0 |
Python |
| Offline Reinforcement Learning (aka Batch Reinforcement Learning) on Atari 2600 games |
