Sciweavers

312 search results - page 21 / 63
» Learning Partially Observable Deterministic Action Models
Sort
View
KI
2005
Springer
14 years 1 months ago
Diagnosis of Plan Execution and the Executing Agent
We discuss the application of Model-Based Diagnosis in (agent-based) planning. Here, a plan together with its executing agent is considered as a system to be diagnosed. It is assum...
Nico Roos, Cees Witteveen
CEEMAS
2005
Springer
14 years 1 months ago
Diagnosis of Plans and Agents
Abstract. We discuss the application of Model-Based Diagnosis in (agentbased) planning. Here, a plan together with its executing agent is considered as a system to be diagnosed. It...
Nico Roos, Cees Witteveen
IROS
2009
IEEE
206views Robotics» more  IROS 2009»
14 years 2 months ago
Bayesian reinforcement learning in continuous POMDPs with gaussian processes
— Partially Observable Markov Decision Processes (POMDPs) provide a rich mathematical model to handle realworld sequential decision processes but require a known model to be solv...
Patrick Dallaire, Camille Besse, Stéphane R...
ICVS
1999
Springer
13 years 12 months ago
Action Reaction Learning: Automatic Visual Analysis and Synthesis of Interactive Behaviour
We propose Action-Reaction Learning as an approach for analyzing and synthesizing human behaviour. This paradigm uncovers causal mappings between past and future events or between...
Tony Jebara, Alex Pentland
COLT
2000
Springer
13 years 12 months ago
Estimation and Approximation Bounds for Gradient-Based Reinforcement Learning
We model reinforcement learning as the problem of learning to control a Partially Observable Markov Decision Process (  ¢¡¤£¦¥§  ), and focus on gradient ascent approache...
Peter L. Bartlett, Jonathan Baxter