加速强化学习跳待用时间的资格传播
Eligibility Propagation to Speed up Time Hopping for Reinforcement Learning
摘要：
提出了一种称为资格传播的机制，以加快用于更快的强化学习在模拟中的跳时技术。资格传播为跳时提供了与资格跟踪为传统强化学习提供的能力类似的能力。它使用状态转换图将值从一个状态传播到其所有时间前任。在一个模拟的爬行机器人上的实验证实，资格传播加速学习过程超过3倍。
英文摘要：
A mechanism called Eligibility Propagation is proposed to speed up the Time Hopping technique used for faster Reinforcement Learning in simulations. Eligibility Propagation provides for Time Hopping similar abilities to what eligibility traces provide for conventional Reinforcement Learning. It propagates values from one state to all of its temporal predecessors using a state transitions graph. Experiments on a simulated biped crawling robot confirm that Eligibility Propagation accelerates the learning process more than 3 times.
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。
