| Name | Version | Summary | date |
| abundant-sdk |
0.2.2 |
Python SDK for the Abundant Environment API - simulation environments for RL agent training |
2025-08-06 01:25:36 |
| polyaxon |
2.9.1 |
Command Line Interface (CLI) and client to interact with Polyaxon API. |
2025-08-01 12:48:58 |
| haupt |
2.9.1 |
Lineage metadata API, artifacts streams, sandbox, ML-API, and spaces for Polyaxon. |
2025-08-01 12:48:55 |
| verifiers |
0.1.2 |
Verifiers for reinforcement learning with LLMs |
2025-07-31 02:37:25 |
| reinforced-lib |
1.2.3 |
Reinforcement learning library |
2025-07-30 10:45:52 |
| autospice |
0.1.5 |
SPICE: Sparse and Interpretable Cognitive Equations |
2025-07-23 16:25:37 |
| rlgym-learn-algos |
0.2.5 |
Algorithm implementations for rlgym-learn |
2025-07-23 03:46:59 |
| toulouse |
1.1.1 |
High-performance card library for ML and RL applications. |
2025-07-21 16:04:10 |
| gama-gymnasium |
0.1.1 |
A Gymnasium environment for reinforcement learning with GAMA agent-based simulations |
2025-07-17 04:09:06 |
| pybandits |
4.0.11 |
Python Multi-Armed Bandit Library |
2025-07-16 10:36:38 |
| arc-advisor |
0.1.0 |
The learning co-pilot for AI agents. Implements the Executor-Advisor pattern for building self-improving agentic systems. |
2025-07-15 02:17:42 |
| rlgym-tools |
2.2.2 |
Extra tools for RLGym. |
2025-02-16 12:07:54 |
| congruent |
0.0.8 |
A CLI for interacting with LLMs, with tracking, validation, integrations, and UI. |
2025-02-12 10:50:00 |
| pokerkit |
0.6.1 |
An open-source Python library for poker game simulations, hand evaluations, and statistical analysis |
2025-01-21 03:34:18 |
| rlportfolio |
0.2.1 |
Reinforcement learning framework for portfolio optimization tasks. |
2025-01-16 04:39:00 |
| adam-robotics |
0.3.3 |
Automatic Differentiation for rigid-body-dynamics AlgorithMs |
2025-01-08 17:28:15 |
| rlgym |
2.0.0 |
A python API with zero dependencies to create fully customizable environments for Reinforcement Learning projects. |
2025-01-06 18:40:24 |
| rlgym-rocket-league |
2.0.0 |
A python API that can be used to treat the game Rocket League as a Gym-like environment for Reinforcement Learning projects. |
2025-01-06 18:40:00 |
| rlgym-api |
2.0.0 |
A python API with zero dependencies to create fully customizable environments for Reinforcement Learning projects. |
2025-01-06 18:39:37 |
| esquilax |
2.0.0 |
JAX multi-agent simulation and ML toolset |
2024-12-21 20:27:42 |