Exploration Conscious Reinforcement Learning Revisited
This work addresses the fundamental exploration-exploitation problem in reinforcement learning for researchers and practitioners, offering an incremental improvement over fixed exploration methods.
The paper tackles the exploration-exploitation tradeoff in reinforcement learning by proposing exploration-conscious criteria that yield optimal policies aligned with the exploration mechanism, and demonstrates that simple modifications to existing algorithms lead to superior performance in both discrete and continuous action spaces.
The Exploration-Exploitation tradeoff arises in Reinforcement Learning when one cannot tell if a policy is optimal. Then, there is a constant need to explore new actions instead of exploiting past experience. In practice, it is common to resolve the tradeoff by using a fixed exploration mechanism, such as $ε$-greedy exploration or by adding Gaussian noise, while still trying to learn an optimal policy. In this work, we take a different approach and study exploration-conscious criteria, that result in optimal policies with respect to the exploration mechanism. Solving these criteria, as we establish, amounts to solving a surrogate Markov Decision Process. We continue and analyze properties of exploration-conscious optimal policies and characterize two general approaches to solve such criteria. Building on the approaches, we apply simple changes in existing tabular and deep Reinforcement Learning algorithms and empirically demonstrate superior performance relatively to their non-exploration-conscious counterparts, both for discrete and continuous action spaces.