search

Unity-Technologies / ml-agents

The Unity Machine Learning Agents Toolkit (ML-Agents) is an open-source project that enables games and simulations to serve as environments for training intelligent agents using deep reinforcement learning and imitation learning.
https://unity.com/products/machine-learning-agents
Other
17.27k stars 4.17k forks source link

Neuroevolution #4597

Closed rdekleijn closed 4 years ago

rdekleijn commented 4 years ago

The ml-agents README.md mentions neuroevolution next to RL and imitation learning as a training method. However, I haven’t been able to find an implementation of neuroevolution (e.g. NEAT) in ml-agents. Is this implemented and am I just missing something, or is this planned for a later release? Or does ml-agents just provide a framework in which I should implement it myself? It’s briefly mentioned here, but wondering if there are any updates. Thanks!

chriselion commented 4 years ago

There are no implementations of this in ml-agents. The intent of the wording there was that you could use the low-level python interface to implement it yourself (but I don't like the wording personally).

chriselion commented 4 years ago

I reworded that section of the readme to clear up the ambiguity: https://github.com/Unity-Technologies/ml-agents/pull/4603 Thanks for pointing it out!

github-actions[bot] commented 3 years ago

This thread has been automatically locked since there has not been any recent activity after it was closed. Please open a new issue for related bugs.