search

rickstaa / stable-learning-control

A framework for training theoretically stable (and robust) Reinforcement Learning control algorithms.
https://rickstaa.dev/stable-learning-control
MIT License
6 stars 1 forks source link

chore(exp): fix CompOscillator learning length #424

Closed rickstaa closed 8 months ago

rickstaa commented 8 months ago

This commit changed the CompOscillator learning length from 1e5 to 2e5. This was done to deal with an inconsistency in Han et al.'s reserach.