| Name | Version | Summary | date |
| plane-env |
0.1.2 |
A reinforcement learning environment for simulating a plane in 2D available, with gymnasium and gymnax support |
2025-09-04 21:45:33 |
| miniworld-maze |
1.3.1 |
Multi-room maze environments from the DrStrategy paper. Provides NineRooms-v0, SpiralNineRooms-v0, and TwentyFiveRooms-v0 gymnasium environments. |
2025-09-03 13:52:41 |
| rlax |
0.1.8 |
A library of reinforcement learning building blocks in JAX. |
2025-09-01 23:40:00 |
| torchrl-nightly |
2025.9.1 |
A modular, primitive-first, python-first PyTorch library for Reinforcement Learning |
2025-09-01 15:24:06 |
| batchBOTS |
0.0.1 |
BOTS |
2025-08-26 20:41:24 |
| mlvlab |
0.2.23 |
Visual AI Ecosystem with Reinforced Learning Simulations based on Gymnasium - MLVisual® |
2025-08-25 18:21:34 |
| LLM4TS |
0.0.1 |
LLM4TS |
2025-08-22 16:16:08 |
| cusrl |
1.1.2 |
Customizable and modular RL algorithms implemented in PyTorch |
2025-08-20 13:27:51 |
| plot-reward-vs-steps |
0.1.1 |
Simple RL reward plotting utility |
2025-08-11 17:19:03 |
| softmax-exploration |
0.1 |
Softmax exploration functions for reinforcement learning |
2025-08-11 03:59:39 |
| gym-zelda-pygame |
0.1.9 |
A ROM-free Zelda-like Gymnasium environment built on Pygame. |
2025-08-10 20:00:02 |
| amp-rsl-rl |
0.2.8 |
Adversarial Motion Prior (AMP) reinforcement learning extension for PPO based on RSL-RL. |
2025-08-04 08:27:43 |
| quoridor-env |
0.2.6 |
Python Quoridor game engine with Gym environment for RL |
2025-07-31 15:29:40 |
| rl-zoo3 |
2.7.0 |
A Training Framework for Stable Baselines3 Reinforcement Learning Agents |
2025-07-25 13:54:25 |
| stable-baselines3 |
2.7.0 |
Pytorch version of Stable Baselines, implementations of reinforcement learning algorithms. |
2025-07-25 09:54:35 |
| sbx-rl |
0.22.0 |
Jax version of Stable Baselines, implementations of reinforcement learning algorithms. |
2025-07-25 09:34:53 |
| rsl-rl-lib |
3.0.0 |
Fast and simple RL algorithms implemented in PyTorch |
2025-07-18 10:12:13 |
| mpcrl |
1.3.3 |
Reinforcement Learning with Model Predictive Control |
2025-07-16 11:57:27 |
| remoterl |
1.1.5 |
RemoteRL: high-performance command-line & Python client with pre-compiled native wheels for remote reinforcement-learning workloads. |
2025-07-16 03:49:51 |
| ale-py |
0.11.2 |
The Arcade Learning Environment (ALE) - a platform for AI research. |
2025-07-12 22:19:16 |