arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2306.04595cs.LGcs.AIcs.RO
收藏

强化学习中跨观测偏移的泛化

Generalization Across Observation Shifts in Reinforcement Learning

Amazon(亚马逊);University of Texas at Austin(德克萨斯大学奥斯汀分校)

Anuj Mahajan, Amy Zhang

AI总结:

本文扩展双模拟框架,通过基于双模拟的新目标学习对上下文相关观测偏移不变的表示,并给出模拟器保真度与策略迁移的理论界,在高维图像控制任务中验证了泛化效果。

摘要:

学习对环境变化具有鲁棒性的策略,对于强化学习智能体的真实世界部署至关重要。这些策略对于在环境偏移之间实现良好泛化也很有必要。我们关注双模拟度量,它为抽象观测中与任务相关的成分,并利用强化学习训练智能体而学习简洁的表示空间提供了一种强有力的手段。在本工作中,我们扩展双模拟框架,使其也能解释依赖于上下文的观测偏移。具体而言,我们聚焦基于模拟器的学习设定,并使用替代观测,通过一种新颖的基于双模拟的目标来学习对观测偏移不变的表示空间。这使我们能够在测试期间将智能体部署到变化的观测设置中,并泛化到未见过的场景。我们还进一步给出了关于模拟器保真度的新理论界,以及将所学策略用于未见过偏移时的性能迁移保证。在基于图像的高维控制域上的实证分析证明了我们方法的有效性。

英文摘要:

Learning policies which are robust to changes in the environment are critical for real world deployment of Reinforcement Learning agents. They are also necessary for achieving good generalization across environment shifts. We focus on bisimulation metrics, which provide a powerful means for abstracting task relevant components of the observation and learning a succinct representation space for training the agent using reinforcement learning. In this work, we extend the bisimulation framework to also account for context dependent observation shifts. Specifically, we focus on the simulator based learning setting and use alternate observations to learn a representation space which is invariant to observation shifts using a novel bisimulation based objective. This allows us to deploy the agent to varying observation settings during test time and generalize to unseen scenarios. We further provide novel theoretical bounds for simulator fidelity and performance transfer guarantees for using a learnt policy to unseen shifts. Empirical analysis on the high-dimensional image based control domains demonstrates the efficacy of our method.

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。

↑