250 search results - page 13 / 50 » Learning action effects in partially observable domains |
ACL
2009
14 years 7 months ago
2009
In this paper, we present a reinforcement learning approach for mapping natural language instructions to sequences of executable actions. We assume access to a reward function tha...
AIED
2005
Springer
15 years 3 months ago
2005
Springer
: Several studies have shown that explaining actions increases students’ knowledge. In this paper, we discuss how NORMIT supports self-explanation. NORMIT is a constraint-based t...
UAI
1994
14 years 11 months ago
1994
Wepresenta symbolicmachinerythatadmits bothprobabilisticand causalinformation abouta givendomainand producesprobabilisticstatementsabouttheeffectofactions andtheimpactof observati...
ATAL
2004
Springer
15 years 3 months ago
2004
Springer
This paper presents properties and results of a new framework for sequential decision-making in multiagent settings called interactive partially observable Markov decision process...
NIPS
2004
14 years 11 months ago
2004
Agents learning to act in a partially observable domain may need to overcome the problem of perceptual aliasing