pogema

[ICLR-2025] POGEMA stands for Partially-Observable Grid Environment for Multiple Agents. This is a grid-based environme…

Python★ 299

gym-environmentmapfmarlpathfindingpo-mapfreinforcement-learningsimulation

c@Cognitive-AI-Systems++

VectorizedMultiAgentSimulator

VMAS is a vectorized differentiable simulator designed for efficient Multi-Agent Reinforcement Learning benchmarking. I…

Python★ 592

gymgym-environmentmarlmulti-agentmulti-agent-learningmulti-agent-reinforcement-learmulti-agent-simulationmulti-agent-systems

p@proroklab++

BenchMARL

BenchMARL is a library for benchmarking Multi-Agent Reinforcement Learning (MARL). BenchMARL allows to quickly compare…

Python★ 647

benchmarkmachine-learningmarlmulti-agentmulti-agent-reinforcement-learpytorchreinforcement-learningrl

f@facebookresearch++

rl

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

Python★ 3.5k

aicontroldecision-makingdistributed-computingmachine-learningmarlmodel-based-reinforcement-learmulti-agent-reinforcement-lear

p@pytorch++

marl-eval

A tool for aggregating and plotting MARL experiment data.

Python★ 86

benchmarkingevaluationexperimentmarlmulti-agent-reinforcement-learmulti-agent-systemsreinforcement-learningresearch

i@instadeepai++

craftium

A framework for creating rich, 3D, Minecraft-like single and multi-agent environments for AI research. (Accepted at ICM…

C++★ 206

artificial-intelligencegymnasiumgymnasium-environmentluantimarlminecraftminetestmulti-agent

m@mikelma++