467 search results - page 63 / 94 » Learning of Agents with Limited Resources |
94
Voted
AAAI
2007
15 years 2 months ago
2007
Concurrent action execution is important for plan-length minimization. However, action specifications are often limited to avoid conflicts arising from precondition/effect inter...
112
Voted
AAAI
1998
15 years 2 months ago
1998
The utility problem occurs when the cost of the acquired knowledge outweighs its bene ts. When the learner acquires control knowledge for speeding up a problem solver, the bene t ...
134
Voted
ICML
1995
IEEE
16 years 1 months ago
1995
IEEE
Partially observable Markov decision processes (pomdp's) model decision problems in which an agent tries to maximize its reward in the face of limited and/or noisy sensor fee...
110
Voted
MLMI
2004
Springer
15 years 6 months ago
2004
Springer
People are emotional, and machines are not. That constrains their communication, and defines a key challenge for the information sciences. Different groups have addressed it from d...
113
Voted
ATAL
2005
Springer
15 years 6 months ago
2005
Springer
Just as POMDPs have been used to reason explicitly about uncertainty in single-agent systems, there has been recent interest in using multi-agent POMDPs to coordinate teams of age...