← Back to List
⚠
Notice:This resource is provided by a third-party author. Please review the code with AI tools or manually before use to ensure security and compatibility.
Pythoninstadeepai/Mava

Mava

🦁 A research-friendly codebase for fast experimentation of multi-agent reinforcement learning in JAX

73.5/100
★ 883Forks: 116
View on GitHub →
Loading report...

Similar Projects

acme

80

A library of reinforcement learning components and agents

Python★ 3.9K

PettingZoo

79

An API standard for multi-agent reinforcement learning environments, with popular reference environments and related utilities

Python★ 3.3K

habitat-lab

81

A modular high-level library to train embodied AI agents across a variety of tasks and environments.

Python★ 2.9K

AgentFlow

64

AgentFlow: In-the-Flow Agentic System Optimization

Python★ 1.6K
← Back to List