action=nan problem - Githubissues

AboudyKreidieh / h-baselines

A repository of high-performing hierarchical reinforcement learning models and algorithms.

MIT License

281 stars 43 forks source link

action=nan problem #250

Open www2171668 opened 2 years ago

www2171668 commented 2 years ago

Hello. When I use run_hrl to run "python run_hrl "HalfCheeth-v2" ", a problem comes with action=nan. It occures in self._policy() of ri_algorithm.py. Of course, run_fcnet is well. How can I deal with it?