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
653 results
[AAAI 2023] Official PyTorch implementation of paper "ACE: Cooperative Multi-agent Q-learning with Bidirectional Action-Dependency".
This repository is for an open-source environment for multi-agent active voltage control on power distribution networks (MAPDN).
Benchmark for Continuous Multi-Agent Robotic Control, based on OpenAI's Mujoco Gym environments.
[NeurIPS 2024] SMART: Scalable Multi-agent Real-time Motion Generation via Next-token Prediction
SIMPL: A Simple and Efficient Multi-agent Motion Prediction Baseline for Autonomous Driving
Find best-response to a fixed policy in multi-agent RL
PRIMAL: Pathfinding via Reinforcement and Imitation Multi-Agent Learning -- Distributed RL/IL code for Multi-Agent Path Finding (MAPF)
A Pytorch implementation of the multi agent deep deterministic policy gradients (MADDPG) algorithm
[ICLR 2026 Blogpost Track Poster] JustRL: Scaling a 1.5B LLM with a Simple RL Recipe
[ICML 2026 Outstanding Paper] Minimalist RL for Diffusion LLMs. 89.1% on GSM8K.
[NeurIPS 2025] Thinkless: LLM Learns When to Think
We perform functional grounding of LLMs' knowledge in BabyAI-Text
llm & rl
siiRL: Shanghai Innovation Institute RL Framework for Advanced LLMs and Multi-Agent Systems
BabyAI platform. A testbed for training agents to understand and execute language commands.
Simple deep Q-learning agent.
Library with search algorithms for task and path planning for multi robot/agent systems
Must-read papers on knowledge graph reasoning
AI Agent that learns how to play Snake with Deep Q-Learning
A collection of multi agent environments based on OpenAI gym.
[NeurIPS 2025 Spotlight] LLM post-training suite — featuring ReasonFlux, ReasonFlux-PRM, and ReasonFlux-Coder.
Single File, Single GPU, From Scratch, Efficient, Full Parameter Tuning library for "RL for LLMs"
RLAnything (ICML 2026) & AutoTool (ICML 2026), DemyAgent: Open-Source RL for LLMs and Agentic Scenarios
Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memory
24,523 repositories in the index in total.
