可靠性调整的优先经验回放
Reliability-Adjusted Prioritized Experience Replay
AI总结：
本文提出ReaPER，通过引入时间差误差可靠性度量，改进优先经验回放，实现更高效的强化学习
摘要：
经验回放使在线强化学习代理能够从过去的经验中高效学习。传统上，经验是均匀地从回放缓冲区中采样，而不考虑经验特定的学习潜力差异。为了更高效地采样，研究者引入了优先经验回放（PER）。在本文中，我们提出了一种PER的扩展，通过引入一个新的时间差误差可靠性度量。我们理论证明，所得到的转换选择算法，即可靠性调整的优先经验回放（ReaPER），比PER更高效。我们进一步展示了ReaPER在各种环境类型中均优于PER，包括Atari-10基准测试。
英文摘要：
Experience replay enables data-efficient learning from past experiences in online reinforcement learning agents. Traditionally, experiences were sampled uniformly from a replay buffer, regardless of differences in experience-specific learning potential. In an effort to sample more efficiently, researchers introduced Prioritized Experience Replay (PER). In this paper, we propose an extension to PER by introducing a novel measure of temporal difference error reliability. We theoretically show that the resulting transition selection algorithm, Reliability-adjusted Prioritized Experience Replay (ReaPER), enables more efficient learning than PER. We further present empirical results showing that ReaPER outperforms PER across various environment types, including the Atari-10 benchmark.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
