The Unity Machine Learning Agents Toolkit (ML-Agents) is an open-source project that enables games and simulations to serve as environments for training intelligent agents using deep reinforcement learning and imitation learning.
Repository Index
132,241 visible repositories in the index
1–24 of 25 · Most stars
PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
- reinforcement-learning
- reinforcement-learning-algorithms
- machine-learning
- gym
A customisable 3D platform for agent-based AI research
Massively Parallel Deep Reinforcement Learning. 🔥
- pytorch
- reinforcement-learning
- ppo
- sac
A fork of OpenAI Baselines, implementations of reinforcement learning algorithms
- reinforcement-learning-algorithms
- reinforcement-learning
- machine-learning
- gym
PyTorch implementation of Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO), Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation (ACKTR) and Generative Adversarial Imitation Learning (GAIL).
- pytorch
- reinforcement-learning
- deep-learning
- deep-reinforcement-learning
TF-Agents: A reliable, scalable and easy to use TensorFlow library for Contextual Bandits and Reinforcement Learning.
- reinforcement-learning
- tensorflow
- contextual-bandits
- bandits
A training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included.
- rl
- reinforcement-learning
- stable-baselines
- openai
A PyTorch Library for Meta-learning Research
- pytorch
- maml
- meta-learning
- learning2learn
Simple and easily configurable grid world environments for reinforcement learning
- gridworld-environment
- gymnasium
- gymnasium-environment
A platform for reproducible world model research and evaluation
- deep-learning
- pytorch
- jepa
- world-model
PyBullet Gymnasium environments for single and multi-agent reinforcement learning of quadcopter control
- pybullet
- crazyflie
- robotics
- reinforcement-learning
Scalable toolkit for efficient model reinforcement
RoboVerse: Towards a Unified Platform, Dataset and Benchmark for Scalable and Generalizable Robot Learning
- imitation-learning
- reinforcement-learning
- robotics
- simulation
[NeurIPS 2025 Spotlight] Reasoning Environments for Reinforcement Learning with Verifiable Rewards
Sim-to-real RL training and deployment tools for the Unitree Go1 robot.
- go1
- sim-to-real
- unitree
- reinforcement-learning
A scalable, agentic-first, and HuggingFace-native RL framework for research (9k lines).
- agentic-rl
- expert-parallelism
- fsdp
- llm
One repository is all that is necessary for Multi-agent Reinforcement Learning (MARL)
- multi-agent-reinforcement-learning
- ray
- rllib
- pytorch
Scalable Multi-Agent RL Training School for Autonomous Driving
- reinforcement-learning
- python
- autonomous-driving
- simulator
Adversarial skill embeddings for training reusable controllers for physically simulated characters.
- animation
- physics-simulation
- reinforcement-learning
A fork of gym-retro with additional games, emulators and supported platforms
- gymnasium
- machine-learning
- reinforcement-learning
- retro
Scalable, event-driven, deep-learning-friendly backtesting library
- reinforcement-learning
- deep-reinforcement-learning
- gym-environment
- openai-gym
A TensorFlow implementation of Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures.
Code for "TD-MPC2: Scalable, Robust World Models for Continuous Control"
- reinforcement-learning
- robotics
- world-model