Sciweavers

46 search results - page 9 / 10
» Discretization of Continuous Action Spaces in Extensive-Form...
Sort
View
IJRR
2011
159views more  IJRR 2011»
13 years 7 days ago
Learning visual representations for perception-action systems
We discuss vision as a sensory modality for systems that effect actions in response to perceptions. While the internal representations informed by vision may be arbitrarily compl...
Justus H. Piater, Sébastien Jodogne, Renaud...
AIPS
2007
13 years 7 months ago
Learning to Plan Using Harmonic Analysis of Diffusion Models
This paper summarizes research on a new emerging framework for learning to plan using the Markov decision process model (MDP). In this paradigm, two approaches to learning to plan...
Sridhar Mahadevan, Sarah Osentoski, Jeffrey Johns,...

Publication
222views
14 years 2 months ago
Algorithms and Bounds for Rollout Sampling Approximate Policy Iteration
Abstract: Several approximate policy iteration schemes without value functions, which focus on policy representation using classifiers and address policy learning as a supervis...
Christos Dimitrakakis, Michail G. Lagoudakis
AAAI
2012
11 years 7 months ago
Characterizing Multi-Agent Team Behavior from Partial Team Tracings: Evidence from the English Premier League
Real-world AI systems have been recently deployed which can automatically analyze the plan and tactics of tennis players. As the game-state is updated regularly at short intervals...
Patrick Lucey, Alina Bialkowski, Peter Carr, Eric ...
ATVA
2007
Springer
115views Hardware» more  ATVA 2007»
13 years 11 months ago
A Compositional Semantics for Dynamic Fault Trees in Terms of Interactive Markov Chains
Abstract. Dynamic fault trees (DFTs) are a versatile and common formalism to model and analyze the reliability of computer-based systems. This paper presents a formal semantics of ...
Hichem Boudali, Pepijn Crouzen, Mariëlle Stoe...