基于强化学习的假设检验
Empirically Verifying Hypotheses Using Reinforcement Learning
摘要:
本文将假设验证作为一个强化学习问题。具体来说,我们的目标是建立一个代理,给定一个关于世界动态的假设,可以采取行动来生成可以帮助预测假设是真还是假的观察。现有的RL算法无法解决这个任务,即使是简单的环境。为了训练智能体,我们利用了许多假设的底层结构,将它们分解为{前置条件,动作序列,后置条件}三元组。通过利用这种结构,我们表明RL代理能够成功完成任务。此外,随后对策略的微调允许代理正确地验证不服从上述因子分解的假设。
英文摘要:
This paper formulates hypothesis verification as an RL problem. Specifically, we aim to build an agent that, given a hypothesis about the dynamics of the world, can take actions to generate observations which can help predict whether the hypothesis is true or false. Existing RL algorithms fail to solve this task, even for simple environments. In order to train the agents, we exploit the underlying structure of many hypotheses, factorizing them as {pre-condition, action sequence, post-condition} triplets. By leveraging this structure we show that RL agents are able to succeed at the task. Furthermore, subsequent fine-tuning of the policies allows the agent to correctly verify hypotheses not amenable to the above factorization.
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。