Showing 2021 · cs.LGShow all
2 papers · 2 filters
cs.LG2021
Actor Loss of Soft Actor Critic Explained
Thibault Lahire
This technical report is devoted to explaining how the actor loss of soft actor critic is obtained, as well as the associated gradient estimate. It gives the necessary mathematical…
cs.LG2021
Large Batch Experience Replay
Thibault Lahire, Matthieu Geist, Emmanuel Rachelson
Several algorithms have been proposed to sample non-uniformly the replay buffer of deep Reinforcement Learning (RL) agents to speed-up learning, but very few theoretical foundation…