| Name | Version | Summary | date |
| adaptiq |
0.12.2 |
An offline Q-learning framework for AI agent prompt optimization. |
2025-07-21 13:57:39 |
| prototwin-gymnasium |
0.2.1 |
The official base Gymnasium environment for ProtoTwin Connect. |
2025-07-18 16:14:05 |
| rlfit |
0.1.1 |
Fitting reinforcement learning model to behavior data under bandits. |
2025-07-18 11:45:08 |
| assume-framework |
0.5.4 |
ASSUME - Agent-Based Electricity Markets Simulation Toolbox |
2025-07-09 06:50:15 |
| neurenix |
1.0.0 |
Empowering Intelligent Futures, One Edge at a Time. |
2025-03-08 01:10:58 |
| qdax |
0.4.1 |
A Python Library for Quality-Diversity and NeuroEvolution |
2025-02-25 18:40:00 |
| pyerualjetwork |
4.6.2 |
PyerualJetwork is a machine learning library supported with GPU(CUDA) acceleration written in Python for professionals and researchers including with PLAN algorithm, PLANEAT algorithm (genetic optimization). Also includes data pre-process and memory manegament |
2025-02-23 14:56:28 |
| PaLM-rlhf-pytorch |
0.5.2 |
PaLM + Reinforcement Learning with Human Feedback - Pytorch |
2025-02-15 18:22:09 |
| SAC-pytorch |
0.0.15 |
Soft Actor Critic - Pytorch |
2025-02-13 14:04:27 |
| craftground |
2.6.8 |
Lightweight Minecraft Environment for Reinforcement Learning |
2025-02-10 04:44:26 |
| bandit-agents |
0.5.23 |
Library to solve k-armed bandit problems |
2025-02-06 23:27:32 |
| pi-optimal |
0.1.2 |
Python package for easy, data-efficient RL-based decision-making in business applications. |
2025-02-06 11:41:28 |
| relab |
0.5.0 |
Reinforcement learning made easy with prebuilt agents, Gym integration, and performance visualization. |
2025-02-01 17:02:37 |
| epyt-control |
0.1.1 |
EPyT-Control -- EPANET Python Toolkit - Control |
2025-02-01 13:48:21 |
| ReplicantDriveSim |
0.5.3 |
A Unity Traffic Simulation |
2025-01-27 13:00:10 |
| rl4co |
0.5.2 |
RL4CO: an Extensive Reinforcement Learning for Combinatorial Optimization Benchmark |
2025-01-26 07:48:28 |
| neurogym |
1.0.6 |
NeuroGym: Gymnasium-style Cognitive Neuroscience Tasks |
2025-01-22 10:06:40 |
| simpliml |
1.2.0 |
Machine Learning, Artificial Intelligence, Mathematics |
2025-01-21 07:17:12 |
| jaxsim |
0.6.1 |
A differentiable physics engine and multibody dynamics library for control and robot learning. |
2025-01-20 09:19:08 |
| poker-reinforcement-learning |
0.1.8 |
Testbed for Reinforcement Learning in Poker. Implemented with Client/Socket technology. |
2025-01-17 04:40:10 |