Hindsight-Combined and Hindsight-Prioritized Experience Replay

• المؤلفون الرئيسيون: Tan, Renzo Roel P, Ikeda, Kazushi, Vergara, John Paul
• التنسيق: text
• منشور في: Archīum Ateneo 2020
• الموضوعات: Experience replay; Deep Q-Network; reinforcement learning; sample efficiency; hybrid algorithm; Logic and Foundations; Mathematics
• الوصول للمادة أونلاين: https://archium.ateneo.edu/mathematics-faculty-pubs/146; https://link.springer.com/chapter/10.1007%2F978-3-030-63833-7_36
• المؤسسة: Ateneo De Manila University

Reinforcement learning has proved to be of great utility; execution, however, may be costly due to sampling inefficiency. An efficient method for training is experience replay, which recalls past experiences. Several experience replay techniques, namely, combined experience replay, hindsight experie...