search

hill-a / stable-baselines

A fork of OpenAI Baselines, implementations of reinforcement learning algorithms
http://stable-baselines.readthedocs.io/
MIT License
4.14k stars 723 forks source link

LinearAnneal #1125

Closed JulioEstebanAsiainNeno closed 3 years ago

JulioEstebanAsiainNeno commented 3 years ago

Hey there! @araffin I've been trying to emulate the following paper: Distributed multi-robot collision avoidance via deep reinforcement learning for navigation in complex scenarios, and it said they used the PPO LinearAnneal function to get the logstd. While checking multiple papers and this github, I haven't been able to find it. I saw on git that you were using LinearAnneal too from the OpenAi environments but I can't seem to find the function. Could you guide me in the correct way so I can find it and use it correctly?

Thanks Julio

araffin commented 3 years ago

Hello, Best for you is to switch to SB3 and use a callback, see related issues: https://github.com/DLR-RM/stable-baselines3/issues/231