Rl Python Packages

torchrl

A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.

judgeval

The Continuous-Improvement Stack for Agents. Our environment data and evals power agent improvement and monitoring.

sb3-contrib

Contrib package for Stable-Baselines3 - Experimental reinforcement learning (RL) code

neptune

📘 The experiment tracker for foundation model training

tianshou

An elegant PyTorch deep reinforcement learning library.

hud-python

OSS RL environment + evals toolkit

neptune-client

📘 The experiment tracker for foundation model training

torchrl-nightly

A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.

dopamine-rl

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

gem-llm

A Gym for Agentic LLMs

rliable

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

torchstudio

Deep Learning Experiment

multi-agent-rlenv

Strongly typed reinforcement learning environment framework

flashbax

⚡ Flashbax: Accelerated Replay Buffers in JAX

rl-zoo3

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

navix

Accelerated minigrid environments with JAX

awex

A high-performance RL training-inference weight synchronization framework, designed to enable second-level parameter updates from training to inference in RL workflows

dsse

The Drone Swarm Search project provides an environment for SAR missions built on PettingZoo, where agents, represented by drones, are tasked with locating targets identified as shipwrecked individuals.

oddish

Run Harbor tasks in the cloud

amp-rsl-rl

🔁 AMP-RSL-RL: Adversarial Motion Priors for robotic RL (PPO + motion imitation)

trianglengin

The core logic for the Triangle Puzzle game. Features a fast C++ backend, Pybind11 wrappers, and a Python API designed for AI/ML development and simulation.

moonfish

~2000 Elo Python Chess Engine that implements: Negamax, PeSTO’s Evaluation, Null Move, Quiescence Search, Lazy SMP.

neodroid

Python interface for the Neodroid platform, an API for communicating with a Unity Game process for a feedback response loop

aenvironment

Standardized environment infrastructure for Agentic AI development.