Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
RL algorithms, environments, simulators and decision-making systems.
Signals: reinforcement-learning, deep-reinforcement-learning, rl, gymnasium, openai-gym, multi-agent-reinforcement-learning, imitation-learning
664 results
Official code for "Self-Distilled Agentic Reinforcement Learning"
Online Goal-Conditioned Reinforcement Learning in JAX. ICLR 2025 Spotlight.
A PyTorch library for all things Reinforcement Learning (RL) for Combinatorial Optimization (CO)
A platform for Reasoning systems (Reinforcement Learning, Contextual Bandits, etc.)
High throughput synchronous and asynchronous reinforcement learning
Implementation of papers in 100 lines of code.
A collection of reinforcement learning environments for simple web interaction tasks
Modular reinforcement learning framework for algorithmic trading
ALMA (Automated meta-Learning of Memory designs for Agentic systems) is a framework that meta-learns memory designs to replace human-engineered designs for agentic system.
Agent Learning Framework https://alf.readthedocs.io
[ICML 2026] Official resources of "Graph-R1: Towards Agentic GraphRAG Framework via End-to-end Reinforcement Learning".
Scaling Deep Research via Reinforcement Learning in Real-world Environments.
Multi-objective Gymnasium environments for reinforcement learning
A reinforcement learning package for Julia
UI-Venus is a general-purpose foundation GUI agent for mobile apps, web platforms, and desktop operating systems using only screenshots as input.
MuZero implementation
Reinforcement Learning for real-time applications
Gibson Environments: Real-World Perception for Embodied Agents
A Real-Time-Strategy game for Deep Learning research
Reinforcement Learning Algorithms Tutorial (Python) from scratch (Mar 2021)
Deep Reinforcement Learning for mobile robot navigation in ROS2 Gazebo simulator. Using DRL (SAC, TD3) neural networks, a robot learns to navigate to a random goal point in a simulated environment while avoiding obstacles.
Native C++ NES emulator with Python/Gymnasium APIs, vector execution, and cross-platform packaging.
Deep learning approach for estimation of Remaining Useful Life (RUL) of an engine
PettingZoo and Gymnasium bindings for popular reinforcement learning environments outside of Farama
24,545 repositories in the index in total.
