Prioritized Sequence Experience Replay

no code implementations • 25 May 2019 • Marc Brittain, Josh Bertram, Xuxi Yang, Peng Wei

Experience replay is widely used in deep reinforcement learning algorithms and allows agents to remember and learn from experiences from the past.

Q-Learning reinforcement-learning +1

Explainable Deterministic MDPs

no code implementations • 9 Jun 2018 • Josh Bertram, Peng Wei

We present a method for a certain class of Markov Decision Processes (MDPs) that can relate the optimal policy back to one or more reward sources in the environment.