cherry icon indicating copy to clipboard operation
cherry copied to clipboard

Published 20 hours ago • verified publisher icon learnables

PPO dual clip

Open MehdiZouitine opened this issue 4 years ago • 0 comments

Description

I added a new option in the PPO loss. This option allows to set up the dual clip PPO (https://arxiv.org/pdf/1912.09729.pdf). This option is very important in complex environments (MOBA, Starcraft and multi-agent environments) because trajectories can be sampled from various source of policies.

image

Contribution Checklist

If your contribution modifies code in the core library (not docs, tests, or examples), please fill the following checklist.

  • [x] My contribution modifies code in the main library.
  • [ ] My modifications are tested.
  • [x] My modifications are documented.

MehdiZouitine avatar Nov 28 '20 12:11 MehdiZouitine