Three Steps at a Time: Learning Representations from Action Sequences in Contrastive RL

By Michal Korniak · Paper · cs.LG

While self-supervised approaches to reinforcement learning have achieved strong results by learning representations of states and actions, a key open question is the time scale over which actions should be modeled. Departing from the standard formulation relying on single-step ac

Cs.lg

View original

HomeResourceLoading…