4817 search results - page 822 / 964 » Learning Models of Intelligent Agents |
150
click to vote
AAAI
2006
15 years 5 months ago
2006
Partially observable Markov decision processes (POMDPs) are an intuitive and general way to model sequential decision making problems under uncertainty. Unfortunately, even approx...
134
click to vote
AAAI
2000
15 years 5 months ago
2000
The game of Hex is a two-player game with simple rules, a deep underlying mathematical beauty, and a strategic complexity comparable to that of Chess and Go. The massive game-tree...
135
click to vote
AAAI
1998
15 years 5 months ago
1998
Manyimportant physical phenomena,such as temperature distribution, air flow, and acoustic waves,are describedas continuous,distributed parameterfields. Analyzingandcontrolling the...
140
click to vote
AAAI
1998
15 years 5 months ago
1998
We present a technique for computing approximately optimal solutions to stochastic resource allocation problems modeled as Markov decision processes (MDPs). We exploit two key pro...
129
click to vote
AAAI
1997
15 years 5 months ago
1997
Partially observable Markov decision processes (POMDPs) allow one to model complex dynamic decision or control problems that include both action outcome uncertainty and imperfect ...