Recall Traces: Backtracking Models for Efficient Reinforcement Learning

Anirudh Goyal, Philemon Brakel, William Fedus, Soumye Singhal, Timothy P. Lillicrap, Sergey Levine, Hugo Larochelle, Yoshua Bengio

Abstract: A backward model of previous (state, action) given the next state, i.e. P(s_t, a_t | s_{t+1}), can be used to simulate additional trajectories terminating at states of interest! Improves RL learning efficiency.