paper-with-me

홈 › Papers

Reasoning about Unforeseen Possibilities During Policy Learning

2018-01-10 · Craig Innes, Alex Lascarides, Stefano V. Albrecht, Subramanian Ramamoorthy, Benjamin Rosman

Methods for learning optimal policies in autonomous agents often assume that the way the domain is conceptualised---its possible states and actions and their causal structure---is known in advance and does not change during learning. This is an unrealistic assumption in many scenarios, because new evidence can reveal important information about what is possible, possibilities that the agent was not aware existed prior to learning. We present a model of an agent which both discovers and learns to exploit unforeseen possibilities using two sources of evidence: direct interaction with the world and communication with a domain expert. We use a combination of probabilistic and symbolic reasoning to estimate all components of the decision problem, including its set of random variables and their causal dependencies. Agent simulations show that the agent converges on optimal polices even when it starts out unaware of factors that are critical to behaving optimally.

📄 PDF Abstract BibTeX arXiv:1801.03331

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Active Inference as the Test-Time Scaling Law for Physical AI Agents

2026-06-22 · Omar Hashash, Christo Kurisummoottil Thomas, Walid Saad, Merouane Debbah 외 arxiv

In this paper, a novel test-time scaling law for physical artificial intelligence (AI) agents is introduced. This scaling law enables physical AI agents to reason with their world models to generalize in unforeseen scena…

Reinforcement LearningBayesian InferenceAutonomous Driving

SECURE: Semantics-aware Embodied Conversation under Unawareness for Lifelong Robot Learning

2024-09-26 · Rimvydas Rubavicius, Peter David Fagan, Alex Lascarides, Subramanian Ramamoorthy

This paper addresses a challenging interactive task learning scenario we call rearrangement under unawareness: to manipulate a rigid-body environment in a context where the agent is unaware of a concept that is key to so…

Novel ConceptsSentence

Formulating Robustness Against Unforeseen Attacks

2022-04-28 · Sihui Dai, Saeed Mahloujifar, Prateek Mittal

Existing defenses against adversarial examples such as adversarial training typically assume that the adversary will conform to a specific or known threat model, such as $\ell_p$ perturbations within a fixed budget. In t…

Multi-Path Collaborative Reasoning via Reinforcement Learning

2025-12-01 · Jindi Lv, Yuhao Zhou, Zheng Zhu, Xiaofeng Wang 외 arxiv

Chain-of-Thought (CoT) reasoning has significantly advanced the problem-solving capabilities of Large Language Models (LLMs), yet conventional CoT often exhibits internal determinism during decoding, limiting exploration…

Reinforcement Learning

Robot Planning and Situation Handling with Active Perception

2026-04-28 · Austine Oloo, Zainab Altaweel, Yohei Hayamizu, Peiqi Liu 외 arxiv

Current robots are capable of computing plans to accomplish complex tasks. However, real-world environments are inherently open and dynamic, and unforeseen situations frequently arise during plan execution, such as jammi…

Motion Planning