Episodic Reinforcement Learning with Expanded State-reward Space

TL;DR

This paper proposes an enhanced episodic control framework for deep reinforcement learning that incorporates historical states and returns into the state-reward space, improving sample efficiency and value estimation.

Contribution

It introduces a novel EC-based DRL method with expanded state-reward space, utilizing retrieved past states and returns to improve policy performance and reduce Q-value overestimation.

Findings

Outperforms recent methods and baselines on Box2d and Mujoco tasks.

Improves sample efficiency and value estimation accuracy.

Alleviates Q-value overestimation in DRL.

Abstract

Empowered by deep neural networks, deep reinforcement learning (DRL) has demonstrated tremendous empirical successes in various domains, including games, health care, and autonomous driving. Despite these advancements, DRL is still identified as data-inefficient as effective policies demand vast numbers of environmental samples. Recently, episodic control (EC)-based model-free DRL methods enable sample efficiency by recalling past experiences from episodic memory. However, existing EC-based methods suffer from the limitation of potential misalignment between the state and reward spaces for neglecting the utilization of (past) retrieval states with extensive information, which probably causes inaccurate value estimation and degraded policy performance. To tackle this issue, we introduce an efficient EC-based DRL framework with expanded state-reward space, where the expanded states used as the input and the expanded rewards used in the training both contain historical and current information. To be specific, we reuse the historical states retrieved by EC as part of the input states and integrate the retrieved MC-returns into the immediate reward in each interactive transition. As a result, our method is able to simultaneously achieve the full utilization of retrieval information and the better evaluation of state values by a Temporal Difference (TD) loss. Empirical results on challenging Box2d and Mujoco tasks demonstrate the superiority of our method over a recent sibling method and common baselines. Further, we also verify our method's effectiveness in alleviating Q-value overestimation by additional experiments of Q-value comparison.