将主动推理融入分布强化学习，提升机器人控制效率。
Distributional Active Inference
- 统一模型基、分布和无模型方法的抽象框架
- 无需建模状态转移即可实现主动推理优势
- 适合需要高效决策的智能体系统研究
复杂环境中的机器人系统在最优控制中面临两大挑战：高效组织感知状态信息与远见式动作规划。传统强化学习仅解决后者，导致样本效率低。主动推理是当前解释生物大脑如何应对这一双重问题的先进过程理论。然而其在人工智能中的应用仍局限于对现有基于模型方法的扩展。本文提出一种强化学习算法的形式化抽象，涵盖基于模型、分布和无模型方法。该抽象将主动推理无缝融入分布强化学习框架，使其性能优势可被利用，而无需建模转移动态。
原文摘要 · Abstract (English)
Optimal control of complex environments with robotic systems faces two complementary and intertwined challenges: efficient organization of sensory state information and far-sighted action planning. Because the reinforcement learning framework addresses only the latter, it tends to deliver sample-inefficient solutions. Active inference is the state-of-the-art process theory that explains how biological brains handle this dual problem. However, its applications to artificial intelligence have thus far been limited to extensions of existing model-based approaches. We present a formal abstraction of reinforcement learning algorithms that spans model-based, distributional, and model-free approaches. This abstraction seamlessly integrates active inference into the distributional reinforcement learning framework, making its performance advantages accessible without transition dynamics modeling.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。