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
16.93k stars 4.13k forks source link

No Example for Behavioral Cloning offline/online training #2508

Closed ghost closed 4 years ago

ghost commented 5 years ago

I have just started working with the Unity ML-Toolkit. I see there are plenty of examples in the ML agents for most of the algorithms, however, none for the behavioral cloning.

I am trying to use offline behavioral cloning method to train a NPC in a FPS game. I don't know how to go around the Academy and Agent Scripts for this and have found neither proper documentation nor remotely close example to be able to understand and reciprocate something similar.

Anyone who has experience with behavioral cloning, please reach out. Any help would be appreciated. Thanks in advance.

chriselion commented 5 years ago

Hi @banish09 The scene in UnitySDK/Assets/ML-Agents/Examples/BananaCollectors/Scenes/BananaIL.unity should be usable with Behavioral Cloning.

There are some sections in the docs https://github.com/Unity-Technologies/ml-agents/blob/develop/docs/Training-Behavioral-Cloning.md and a related section on recording demonstrations https://github.com/Unity-Technologies/ml-agents/blob/develop/docs/Training-Imitation-Learning.md#recording-demonstrations that might be helpful.

Note that there was a bug in the 0.9.2 release that broke BC. We just released a bugfix release (0.9.3) that addresses this.

You may also want to look into GAIL as an alternative to BC: https://github.com/Unity-Technologies/ml-agents/blob/develop/docs/Reward-Signals.md#gail-reward-signal

stale[bot] commented 4 years ago

This issue has been automatically marked as stale because it has not had activity in the last 14 days. It will be closed in the next 14 days if no further activity occurs. Thank you for your contributions.

stale[bot] commented 4 years ago

This issue has been automatically closed because it has not had activity in the last 28 days. If this issue is still valid, please ping a maintainer. Thank you for your contributions.

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.