可观测性
强化学习
状态空间
空格(标点符号)
国家(计算机科学)
钢筋
人工智能
计算机科学
数学
应用数学
算法
心理学
社会心理学
统计
操作系统
作者
Carlos E. Luis,Alessandro G. Bottero,Julia Vinogradska,Felix Berkenkamp,Jan Peters
标识
DOI:10.48550/arxiv.2409.16824
摘要
Optimal decision-making under partial observability requires reasoning about the uncertainty of the environment's hidden state. However, most reinforcement learning architectures handle partial observability with sequence models that have no internal mechanism to incorporate uncertainty in their hidden state representation, such as recurrent neural networks, deterministic state-space models and transformers. Inspired by advances in probabilistic world models for reinforcement learning, we propose a standalone Kalman filter layer that performs closed-form Gaussian inference in linear state-space models and train it end-to-end within a model-free architecture to maximize returns. Similar to efficient linear recurrent layers, the Kalman filter layer processes sequential data using a parallel scan, which scales logarithmically with the sequence length. By design, Kalman filter layers are a drop-in replacement for other recurrent layers in standard model-free architectures, but importantly they include an explicit mechanism for probabilistic filtering of the latent state representation. Experiments in a wide variety of tasks with partial observability show that Kalman filter layers excel in problems where uncertainty reasoning is key for decision-making, outperforming other stateful models.
科研通智能强力驱动
Strongly Powered by AbleSci AI