arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2202.06557cs.LGcs.AI
收藏

离散马尔可夫上下文演化下的强化学习

Reinforcement Learning in Presence of Discrete Markovian Context Evolution

Huawei UK R&D(华为英国研发中心);University of Cambridge(剑桥大学);University College London(伦敦大学学院)

Hang Ren, Aivar Sootla, Taher Jafferjee, Junxiao Shen, Jun Wang, Haitham Bou-Ammar

摘要:

我们考虑一个上下文相关的强化学习(RL)设置,其特征在于:a)未知的有限数量的不可直接观察的上下文; b)突然(不连续)的上下文变化发生在一个情节;和c)马尔可夫上下文进化。我们认为,这种具有挑战性的情况下,经常遇到的应用程序,我们解决它使用贝叶斯方法和变分推理。我们采用粘性分层狄利克雷过程(HDP)之前的模型学习,这可以说是最适合马尔可夫过程建模。然后,我们推导出一个上下文蒸馏过程,它识别和删除虚假的上下文在一个无监督的方式。我们认为,这两个组件的组合允许从数据中推断出上下文的数量,从而处理上下文基数假设。然后,我们找到的最佳策略,使有效的策略学习使用现成的RL算法的表示。最后,我们经验证明(使用健身房环境推车杆摆动,无人机,十字路口),我们的方法成功的国家的最先进的方法的其他框架失败,并详细说明这种失败的原因。

英文摘要:

We consider a context-dependent Reinforcement Learning (RL) setting, which is characterized by: a) an unknown finite number of not directly observable contexts; b) abrupt (discontinuous) context changes occurring during an episode; and c) Markovian context evolution. We argue that this challenging case is often met in applications and we tackle it using a Bayesian approach and variational inference. We adapt a sticky Hierarchical Dirichlet Process (HDP) prior for model learning, which is arguably best-suited for Markov process modeling. We then derive a context distillation procedure, which identifies and removes spurious contexts in an unsupervised fashion. We argue that the combination of these two components allows to infer the number of contexts from data thus dealing with the context cardinality assumption. We then find the representation of the optimal policy enabling efficient policy learning using off-the-shelf RL algorithms. Finally, we demonstrate empirically (using gym environments cart-pole swing-up, drone, intersection) that our approach succeeds where state-of-the-art methods of other frameworks fail and elaborate on the reasons for such failures.

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。

↑