变化稀疏报酬环境下的自适应方差
Adaptive Variance for Changing Sparse-Reward Environments
摘要:
被训练在固定环境中执行任务的机器人在面对环境的意外变化时,由于缺乏探索,往往会失败。我们提出了一个原则性的方法来适应政策,以更好地探索不断变化的稀疏奖励环境。不同于以往的作品,明确地模拟环境的变化,我们分析了价值函数和最优探索的高斯参数化的政策之间的关系,并表明我们的理论导致一个有效的策略,调整方差的政策,使快速适应各种稀疏回报环境的变化。
英文摘要:
Robots that are trained to perform a task in a fixed environment often fail when facing unexpected changes to the environment due to a lack of exploration. We propose a principled way to adapt the policy for better exploration in changing sparse-reward environments. Unlike previous works which explicitly model environmental changes, we analyze the relationship between the value function and the optimal exploration for a Gaussian-parameterized policy and show that our theory leads to an effective strategy for adjusting the variance of the policy, enabling fast adapt to changes in a variety of sparse-reward environments.
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。