arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2406.18293cs.LGcs.AI
收藏

结合超参数与奖励形状的自动化优化

Combining Automated Optimisation of Hyperparameters and Reward Shape

RWTH Aachen University(亚琛工业大学);Universiteit Leiden(莱顿大学)

Julian Dierkes, Emma Cramer, Holger H. Hoos, Sebastian Trimpe

AI总结:

针对强化学习中超参数与奖励函数难调优且相互依赖的问题,提出二者联合优化方法并加入方差惩罚提升策略稳定性,实验证明其在多数环境中性能提升显著且计算成本增加少。

摘要:

近年来,深度强化学习(RL)取得了显著进展。然而,即便对于专家而言,找到合适的超参数配置和奖励函数仍颇具挑战,且模型性能高度依赖这些设计选择。此外,大多数RL研究都是在已知基准上开展的,而这些基准已经存在关于上述选择的先验知识。但在新型实际应用中,任务往往十分复杂,不存在关于优良超参数和奖励函数的先验知识,因此需要从零推导它们。已有研究分别对超参数或奖励函数的自动调优进行了单独探索。我们通过实验证明,RL算法的超参数配置与奖励函数通常相互依赖,这意味着若其中一方取值不当,另一方就无法实现完全优化。随后,我们提出了一种超参数与奖励函数联合优化的方法。此外,我们将方差惩罚作为优化目标纳入其中,以提升所学策略的稳定性。我们使用Proximal Policy Optimisation(近端策略优化)和Soft Actor-Critic(软演员-评论家算法)在四个环境中开展了大量实验。结果表明,联合优化在半数环境中显著优于基线性能,在其余环境中也能达到具有竞争力的性能,且计算成本仅略有增加。这表明联合优化应成为最佳实践。

英文摘要:

There has been significant progress in deep reinforcement learning (RL) in recent years. Nevertheless, finding suitable hyperparameter configurations and reward functions remains challenging even for experts, and performance heavily relies on these design choices. Also, most RL research is conducted on known benchmarks where knowledge about these choices already exists. However, novel practical applications often pose complex tasks for which no prior knowledge about good hyperparameters and reward functions is available, thus necessitating their derivation from scratch. Prior work has examined automatically tuning either hyperparameters or reward functions individually. We demonstrate empirically that an RL algorithm's hyperparameter configurations and reward function are often mutually dependent, meaning neither can be fully optimised without appropriate values for the other. We then propose a methodology for the combined optimisation of hyperparameters and the reward function. Furthermore, we include a variance penalty as an optimisation objective to improve the stability of learned policies. We conducted extensive experiments using Proximal Policy Optimisation and Soft Actor-Critic on four environments. Our results show that combined optimisation significantly improves over baseline performance in half of the environments and achieves competitive performance in the others, with only a minor increase in computational costs. This suggests that combined optimisation should be best practice.

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。

↑