Picture for Bekzhan Kerimkulov

Bekzhan Kerimkulov

A Fisher-Rao gradient flow for entropy-regularised Markov decision processes in Polish spaces

Add code
Oct 04, 2023
Viaarxiv icon

Convergence of policy gradient for entropy regularized MDPs with neural network approximation in the mean-field regime

Add code
Jan 18, 2022
Viaarxiv icon