2022/05/18 by Ryan Sander, Sander, Ryan, Wilko Schwarting +9 · 1 citation
Computer Science · Psychology · #FOS: Computer and information sciences #FOS: Electrical engineering #Machine Learning (cs.LG) #Mental Health Research Topics #Reinforcement Learning in Robotics #Robotics (cs.RO) #Systems and Control (eess.SY) #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2205.09117
openalex publication_date 2022/05/18 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Experience replay plays a crucial role in improving the sample efficiency of deep reinforcement learning agents. Recent advances in experience replay propose using Mixup (Zhang et al., 2018) to further improve sample efficiency via synthetic sample generation. We build upon this technique with Neighborhood Mixup Experience Replay (NMER), a geometrically-grounded replay buffer that interpolates transitions with their closest neighbors in state-action space. NMER preserves a locally linear approximation of the transition manifold by only applying Mixup between transitions with vicinal state-action features. Under NMER, a given transition's set of state action neighbors is dynamic and episode agnostic, in turn encouraging greater policy generalizability via inter-episode interpolation. We combine our approach with recent off-policy deep reinforcement learning algorithms and evaluate on continuous control environments. We observe that NMER improves sample efficiency by an average 94% (TD3) and 29% (SAC) over baseline replay buffers, enabling agents to effectively recombine previous experiences and learn from limited data.