Sciweavers

Share
30 search results - page 1 / 6
» On discovery and learning of models with predictive represen...
Sort
View
ATAL
2007
Springer
8 years 8 months ago
On discovery and learning of models with predictive representations of state for agents with continuous actions and observations
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...
David Wingate, Satinder P. Singh
ICML
2004
IEEE
9 years 5 months ago
Learning and discovery of predictive state representations in dynamical systems with reset
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...
Michael R. James, Satinder P. Singh
AAAI
2011
7 years 4 months ago
Combining Learned Discrete and Continuous Action Models
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...
Joseph Z. Xu, John E. Laird
ATAL
2010
Springer
8 years 5 months ago
Closing the learning-planning loop with predictive state representations
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 ...
Byron Boots, Sajid M. Siddiqi, Geoffrey J. Gordon
AAAI
2006
8 years 5 months ago
Learning Partially Observable Action Models: Efficient Algorithms
We present tractable, exact algorithms for learning actions' effects and preconditions in partially observable domains. Our algorithms maintain a propositional logical repres...
Dafna Shahaf, Allen Chang, Eyal Amir
books