arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2201.02628cs.LGcs.AI
收藏

注意力选项-评论家

Attention Option-Critic

McGill University(麦吉尔大学);Mila(米拉研究所);Google Deepmind(谷歌DeepMind)

Raviteja Chunduru, Doina Precup

摘要:

强化学习中的时间抽象是智能体学习和使用高级行为的能力,称为选项。option-critic架构提供了一种基于梯度的端到端学习方法来构建选项。我们提出了一个基于注意力的扩展这个框架,它使代理学习集中不同的选项在观察空间的不同方面。我们表明,这导致行为上的不同的选项,也能够状态抽象,并防止退化问题的选项统治和频繁的选项切换发生在选项批评,同时实现类似的样本复杂性。我们还证明了更有效的,可解释的,和可重用的性质相比,通过不同的迁移学习任务的选择的选择。实验结果在一个相对简单的四个房间的环境和更复杂的ALE(商场学习环境)展示了我们的方法的有效性。

英文摘要:

Temporal abstraction in reinforcement learning is the ability of an agent to learn and use high-level behaviors, called options. The option-critic architecture provides a gradient-based end-to-end learning method to construct options. We propose an attention-based extension to this framework, which enables the agent to learn to focus different options on different aspects of the observation space. We show that this leads to behaviorally diverse options which are also capable of state abstraction, and prevents the degeneracy problems of option domination and frequent option switching that occur in option-critic, while achieving a similar sample complexity. We also demonstrate the more efficient, interpretable, and reusable nature of the learned options in comparison with option-critic, through different transfer learning tasks. Experimental results in a relatively simple four-rooms environment and the more complex ALE (Arcade Learning Environment) showcase the efficacy of our approach.

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。

↑