任意依赖反应环境中学习的可能性
On the Possibility of Learning in Reactive Environments with Arbitrary Dependence
摘要：
我们解决了强化学习的问题，其中观测可能表现出对过去观测和动作的任意形式的随机依赖性，即比（PO）MDP更一般的环境。智能体的任务是在真实生成环境未知但属于已知可数环境族的情况下获得最佳可能的渐近奖励。我们找到了一些充分条件下存在的代理，达到最好的渐近回报的任何环境中的类环境。我们分析了这些条件的紧密程度，以及它们与强化学习和相关领域中已知的不同概率假设（如马尔可夫决策过程和混合条件）的关系。
英文摘要：
We address the problem of reinforcement learning in which observations may exhibit an arbitrary form of stochastic dependence on past observations and actions, i.e. environments more general than (PO)MDPs. The task for an agent is to attain the best possible asymptotic reward where the true generating environment is unknown but belongs to a known countable family of environments. We find some sufficient conditions on the class of environments under which an agent exists which attains the best asymptotic reward for any environment in the class. We analyze how tight these conditions are and how they relate to different probabilistic assumptions known in reinforcement learning and related fields, such as Markov Decision Processes and mixing conditions.
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。
