54 search results - page 6 / 11 » Planning with POMDPs Using a Compact, Logic-Based Representa... |
NIPS
2004
13 years 8 months ago
2004
Schema learning is a way to discover probabilistic, constructivist, predictive action models (schemas) from experience. It includes methods for finding and using hidden state to m...
ECP
1997
Springer
13 years 11 months ago
1997
Springer
We present a framework for encoding planning problems in logic programs with negation as failure, having computational e ciency as our major consideration. In order to accomplish o...
AIPS
2007
13 years 9 months ago
2007
In sequential decision-making problems formulated as Markov decision processes, state-value function approximation using domain features is a critical technique for scaling up the...
ICMI
2005
Springer
14 years 1 months ago
2005
Springer
Situated, spontaneous speech may be ambiguous along acoustic, lexical, grammatical and semantic dimensions. To understand such a seemingly difficult signal, we propose to model th...
AAAI
2010
13 years 9 months ago
2010
Finite-state controllers represent an effective action selection mechanisms widely used in domains such as video-games and mobile robotics. In contrast to the policies obtained fr...