1 problem

0 votes0 replies0 views
Entropy regularization conjecture for stochastic REINFORCE
In a finite Markov decision process, consider stochastic REINFORCE with entropy regularization and the uniformly bounded texttt{PostProcess} steps in Algorithm PGphased. Entropy re…
Conjectureopenentropy-regularization policy-gradient-methods reinforcement-learningarXiv posted 2 days ago

Entropy regularization conjecture for stochastic REINFORCE