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 60 · Most stars
A standard API for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)
StarCraft II Learning Environment
- reinforcement-learning
- machine-learning
- starcraft-ii
- starcraft-ii-replays
PyTorch implementations of deep reinforcement learning algorithms and environments
OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.
- games
- reinforcement-learning
- multiagent
- cpp
Google DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo.
Reinforcement Learning / AI Bots in Card (Poker) Games - Blackjack, Leduc, Texas, DouDizhu, Mahjong, UNO.
- reinforcement-learning
- deep-reinforcement-learning
- game-ai
- poker
A standard API for multi-agent reinforcement learning environments, with popular reference environments and related utilities
- api
- gymnasium
- multi-agent-reinforcement-learning
- reinforcement-learning
A collection of environments for autonomous driving and tactical decision-making tasks
- reinforcement-learning
- autonomous-driving
- gymnasium-environment
Isaac Gym Environments for Legged Robots
A modular high-level library to train embodied AI agents across a variety of tasks and environments.
- ai
- computer-vision
- robotics
- simulator
RL training environments for Microduck (mjlab)
A training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included.
- rl
- reinforcement-learning
- stable-baselines
- openai
An interface library for RL post training with environments.
Simple and easily configurable grid world environments for reinforcement learning
- gridworld-environment
- gymnasium
- gymnasium-environment
A simple framework that allows researchers and hobbyists to develop AI agents for Atari 2600 games
The most simple, flexible, and comprehensive OpenAI Gym trading environment (Approved by OpenAI Gym)
- openai-gym
- reinforcement-learning
- q-learning
- dqn
PyBullet Gymnasium environments for single and multi-agent reinforcement learning of quadcopter control
- pybullet
- crazyflie
- robotics
- reinforcement-learning
DIAMOND (DIffusion As a Model Of eNvironment Dreams) is a reinforcement learning agent trained in a diffusion world model. NeurIPS 2024 Spotlight.
Reinforcement Learning environments based on the 1993 game Doom :godmode:
- deep-learning
- reinforcement-learning
- python
- vizdoom
FinRL®-Meta: Dynamic datasets and market environments for FinRL.
A collection of robotics simulation environments for reinforcement learning
- d4rl
- gymnasium
- mujoco
- reinforcement-learning
Trading and Backtesting environment for training reinforcement learning agent or simple rule base algo.
Collections of robotics environments geared towards benchmarking multi-task and meta reinforcement learning
- meta-rl
- multi-task
- benchmark-environments
- mujoco