OHCAM：通过不确定性引导探索学习带条件与量化效应的动作模型
Learning Action Models with Conditional and Quantified Effects via Uncertainty-Guided Exploration
AI 导读
研究者提出 OHCAM，一种在线学习方法，可从与环境的有限交互中学习带条件与量化效应的动作模型。该方法在竞争性假设间最大化分歧以主动选择信息量大的动作，对观测噪声鲁棒，并从小规模简单假设出发按需扩展以提升可扩展性。在六个基准规划域上，OHCAM 样本效率高于基线，并通过 Kinova Gen3 机器人在两项任务上验证了实际适用性。
正文 · 原文
Abstract:Accurate action models are critical for effective planning. Existing action-model learning methods largely assume simple action representations or become computationally intractable when learning conditional and quantified effects. We present Online Hypothesis-Driven Conditional Action Model Learning (OHCAM), an online approach for learning action models with conditional and quantified effects from limited interactions with the environment. OHCAM maintains a belief over hypothesized action models and actively selects informative actions to reduce uncertainty by maximizing disagreement among competing hypotheses, while being robust to noisy observations. To enable scalability, OHCAM begins with a small set of simple action model hypotheses and expands to more complex conditions only when the current hypotheses become inconsistent with the data. Experiments on six benchmark planning domains demonstrate that OHCAM is sample efficient in learning action models that solve substantially more tasks than baselines, even with observation noise. We validate OHCAM on two tasks using a Kinova Gen3 robot, demonstrating the real-world applicability of our approach.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2608.30955 [cs.AI] |
| (or arXiv:2608.30955v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2608.30955 arXiv-issued DOI via DataCite |
Submission history
From: Jeffrey Jewett [view email]
[v1]
Mon, 31 Aug 2026 15:23:43 UTC (7,636 KB)
[v2]
Mon, 9 Nov 2026 20:04:24 UTC (7,638 KB)
来源：arXiv cs.AI · arxiv.org