万变中的恒定
Constant in an Ever-Changing World
AI总结：
针对强化学习训练振荡导致的不稳定与性能下降问题，提出CIC框架，通过双策略选择性更新与自适应调整机制增强稳定性，在5个MuJoCo环境上验证其可无额外成本提升传统算法性能。
摘要：
强化学习的训练过程常出现严重振荡，导致不稳定且性能下降。本文提出Constant in an Ever-Changing World（CIC，万变中的恒定）框架，通过增强算法稳定性来提升性能。CIC同时维护一个代表性策略和一个当前策略，它不会盲目更新代表性策略，而是仅在当前策略表现更优时才选择性更新。此外，CIC采用自适应调整机制，让代表性策略与当前策略共同助力 critic 训练。我们在5个MuJoCo环境上对CIC进行了评估，结果表明CIC能在不产生额外计算成本的情况下提升传统算法的性能。
英文摘要：
The training process of reinforcement learning often suffers from severe oscillations, leading to instability and degraded performance. In this paper, we propose a Constant in an Ever-Changing World (CIC) framework that enhances algorithmic stability to improve performance. CIC maintains both a representative policy and a current policy. Instead of updating the representative policy blindly, CIC selectively updates it only when the current policy demonstrates superiority. Furthermore, CIC employs an adaptive adjustment mechanism, enabling the representative and current policies to jointly facilitate critic training. We evaluate CIC on five MuJoCo environments, and the results show that CIC improves the performance of conventional algorithms without incurring additional computational cost.
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。
