arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2302.09601cs.LGcs.CV
收藏

基于奖励序列分布的视觉强化学习泛化

Generalization in Visual Reinforcement Learning with the Reward Sequence Distribution

University of Science and Technology of China(中国科学技术大学);Hefei Comprehensive National Science Center(合肥综合性国家科学中心);Texas A&M University(德州农工大学)

Jie Wang, Rui Yang, Zijie Geng, Zhihao Shi, Mingxuan Ye, Qi Zhou, Shuiwang Ji, Bin Li, Yongdong Zhang, Feng Wu

摘要:

部分可观察马尔可夫决策过程(POMDP)的泛化对于视觉强化学习(VRL)在实际场景中的成功应用至关重要。一个广泛使用的想法是学习任务相关的表示,其编码POMDP中的共同特征的任务相关信息,即,奖励和过渡动态。由于潜在状态空间中的过渡动态-这是任务相关的和不变的视觉干扰-是未知的代理,现有的方法交替使用过渡动态的观察空间中提取任务相关的信息过渡动态。然而,在观察空间中的这种过渡动态涉及任务无关的视觉干扰,降低了VRL方法的泛化性能。为了解决这个问题,我们提出了奖励序列分布条件下的开始观察和预定义的后续行动序列(RSD-OA)。RSD-OA的吸引人的特征包括:(1)RSD-OA对视觉干扰是不变的,因为它以预定义的后续动作序列为条件,而没有来自过渡动态的任务无关信息,以及(2)奖励序列在奖励和过渡动态中捕获长期任务相关信息。实验表明,我们基于RSD-OA的表示学习方法显著提高了在不可见环境中的泛化性能,在具有视觉干扰的DeepMind Control任务中的表现优于几种最先进的方法。

英文摘要:

Generalization in partially observed markov decision processes (POMDPs) is critical for successful applications of visual reinforcement learning (VRL) in real scenarios. A widely used idea is to learn task-relevant representations that encode task-relevant information of common features in POMDPs, i.e., rewards and transition dynamics. As transition dynamics in the latent state space -- which are task-relevant and invariant to visual distractions -- are unknown to the agents, existing methods alternatively use transition dynamics in the observation space to extract task-relevant information in transition dynamics. However, such transition dynamics in the observation space involve task-irrelevant visual distractions, degrading the generalization performance of VRL methods. To tackle this problem, we propose the reward sequence distribution conditioned on the starting observation and the predefined subsequent action sequence (RSD-OA). The appealing features of RSD-OA include that: (1) RSD-OA is invariant to visual distractions, as it is conditioned on the predefined subsequent action sequence without task-irrelevant information from transition dynamics, and (2) the reward sequence captures long-term task-relevant information in both rewards and transition dynamics. Experiments demonstrate that our representation learning approach based on RSD-OA significantly improves the generalization performance on unseen environments, outperforming several state-of-the-arts on DeepMind Control tasks with visual distractions.

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。

↑