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.
Pythongoogle-deepmind/acme

acme

A library of reinforcement learning components and agents

80.1/100
3.9KForks: 533
View on GitHub
Loading report...

Similar Projects

habitat-lab

81

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

Python2.9K

company-research-agent

80

An agentic company research tool powered by LangGraph and Tavily that conducts deep diligence on companies using a multi-agent framework. It leverages Google's Gemini 2.5 Flash and OpenAI's GPT-5.1 on the backend for inference.

Python1.6K

Mava

74

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

Python883

stable-baselines3-contrib

73

Contrib package for Stable-Baselines3 - Experimental reinforcement learning (RL) code

Python693
Back to List