Abstract:
Experience replay is central to off-policy algorithms in deep reinforcement learning (RL), but there remain significant gaps in our understanding. We therefore present a systematic and extensive analysis of experience replay in Q-learning methods, focusing on two fundamental properties: the replay capacity and the ratio of learning updates to experience collected (replay ratio). Our additive and ablative studies upend conventional wisdom around experience replay - greater capacity is found to substantially increase the performance of certain algorithms, while leaving others unaffected. Counter-intuitively we show that theoretically ungrounded, uncorrected n-step returns are uniquely beneficial while other techniques confer limited benefit for sifting through larger memory. Separately by directly controlling the replay ratio
we contextualize previous observations in the literature and empirically measure the importance across three deep RL algorithms. Finally, we conclude by testing a set of hypotheses on the nature of these performance benefits.
