GA + DDPG + HER:基于遗传算法的深度强化学习函数优化器
GA+DDPG+HER: Genetic Algorithm-Based Function Optimizer in Deep Reinforcement Learning for Robotic Manipulation Tasks
摘要:
代理可以基于奖励函数使用强化学习(RL)做出决策。然而,学习算法参数的值的选择可以对整个学习过程具有实质性影响。为了发现接近最优的学习参数值,我们扩展了我们以前提出的基于遗传算法的深度确定性策略梯度和后见之明经验重放方法(简称为GA+DDPG+HER)。在FetchReach,FetchSlide,FetchPush,FetchPick&Place和DoorOpening的机器人操作任务上,我们应用了GA+DDPG+HER方法。我们的技术GA+DDPG+HER也用于AuboReach环境中,进行了一些调整。我们的实验分析表明,我们的方法产生的性能是明显更好,发生速度比原来的算法。我们还提供了GA+DDPG+HER击败当前方法的证据。最后的结果支持我们的断言,并提供了足够的证据,自动化的参数调整过程是至关重要的,并减少学习时间高达57%。
英文摘要:
Agents can base decisions made using reinforcement learning (RL) on a reward function. The selection of values for the learning algorithm parameters can, nevertheless, have a substantial impact on the overall learning process. In order to discover values for the learning parameters that are close to optimal, we extended our previously proposed genetic algorithm-based Deep Deterministic Policy Gradient and Hindsight Experience Replay approach (referred to as GA+DDPG+HER) in this study. On the robotic manipulation tasks of FetchReach, FetchSlide, FetchPush, FetchPick&Place, and DoorOpening, we applied the GA+DDPG+HER methodology. Our technique GA+DDPG+HER was also used in the AuboReach environment with a few adjustments. Our experimental analysis demonstrates that our method produces performance that is noticeably better and occurs faster than the original algorithm. We also offer proof that GA+DDPG+HER beat the current approaches. The final results support our assertion and offer sufficient proof that automating the parameter tuning procedure is crucial and does cut down learning time by as much as 57%.
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。