Models of agent-environment interaction that use predictive state representations (PSRs) have mainly focused on the case of discrete observations and actions. The theory of discre...
Predictive state representations (PSRs) are a recently proposed way of modeling controlled dynamical systems. PSR-based models use predictions of observable outcomes of tests that...
Action modeling is an important skill for agents that must perform tasks in novel domains. Previous work on action modeling has focused on learning STRIPS operators in discrete, r...
A central problem in artificial intelligence is to choose actions to maximize reward in a partially observable, uncertain environment. To do so, we must learn an accurate model of ...
We present tractable, exact algorithms for learning actions' effects and preconditions in partially observable domains. Our algorithms maintain a propositional logical repres...