Neighboring State-based Exploration for Reinforcement Learning
This addresses exploration challenges in reinforcement learning for decision-making tasks, but it appears incremental as it builds on existing model-free approaches.
The paper tackled the exploration-exploitation trade-off in reinforcement learning by proposing neighboring state-based exploration methods, resulting in one method outperforming Double DQN by 49% in eval reward return in a discrete environment.
Reinforcement Learning is a powerful tool to model decision-making processes. However, it relies on an exploration-exploitation trade-off that remains an open challenge for many tasks. In this work, we study neighboring state-based, model-free exploration led by the intuition that, for an early-stage agent, considering actions derived from a bounded region of nearby states may lead to better actions when exploring. We propose two algorithms that choose exploratory actions based on a survey of nearby states, and find that one of our methods, $ρ$-explore, consistently outperforms the Double DQN baseline in an discrete environment by 49% in terms of Eval Reward Return.