提出新模型让智能体在环境变化时仍稳定决策
Distributionally Robust Free Energy Principle for Decision-Making
- 基于鲁棒自由能原理构建决策框架
- 在分布外测试中表现优于现有先进模型
- 适合需高可靠性的自主系统部署
尽管自主智能体表现出色，但在训练与实际环境不一致时可能产生异常行为，甚至导致灾难性失败。对训练-环境差异的鲁棒性是智能体实现真实部署的核心要求，但长期未能解决。本文提出分布鲁棒自由能模型（DR-FREE），通过结合鲁棒自由能原理与求解引擎，将鲁棒性内置于决策机制。在基准实验中，当现有先进模型失败时，DR-FREE仍能完成任务。这一突破或可推动多智能体系统的实际应用，并为自然智能体（无需大量训练）如何在多变环境中生存提供新思路。
原文摘要 · Abstract (English)
Despite their groundbreaking performance, autonomous agents can misbehave when training and environmental conditions become inconsistent, with minor mismatches leading to undesirable behaviors or even catastrophic failures. Robustness towards these training-environment ambiguities is a core requirement for intelligent agents and its fulfillment is a long-standing challenge towards their real-world deployments. Here, we introduce a Distributionally Robust Free Energy model (DR-FREE) that instills this core property by design. Combining a robust extension of the free energy principle with a resolution engine, DR-FREE wires robustness into the agent decision-making mechanisms. Across benchmark experiments, DR-FREE enables the agents to complete the task even when, in contrast, state-of-the-art models fail. This milestone may inspire both deployments in multi-agent settings and, at a perhaps deeper level, the quest for an explanation of how natural agents -- with little or no training -- survive in capricious environments.
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。