Reasoning about Unforeseen Possibilities During Policy Learning
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Active Inference as the Test-Time Scaling Law for Physical AI Agents
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 DrivingSECURE: Semantics-aware Embodied Conversation under Unawareness for Lifelong Robot Learning
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 ConceptsSentenceFormulating Robustness Against Unforeseen Attacks
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
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 LearningRobot Planning and Situation Handling with Active Perception
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