829 search results - page 15 / 166 » A time aggregation approach to Markov decision processes |
IJCAI
1997
15 years 1 months ago
1997
Decision making based on the comparison of multiple criteria of two or more alternatives, is the subject of intensive research. In many decision making situations, a single criter...
COLT
2000
Springer
15 years 4 months ago
2000
Springer
We model reinforcement learning as the problem of learning to control a Partially Observable Markov Decision Process ( ¢¡¤£¦¥§ ), and focus on gradient ascent approache...
110
click to vote
AAAI
2011
13 years 11 months ago
2011
In environmental and natural resource planning domains actions are taken at a large number of locations over multiple time periods. These problems have enormous state and action s...
ICALP
2009
Springer
16 years 2 days ago
2009
Springer
We define stochastic timed games, which extend two-player timed games with probabilities (following a recent approach by Baier et al), and which extend in a natural way continuous-...
ML
2002
ACM
14 years 11 months ago
2002
ACM
We present new algorithms for reinforcement learning, and prove that they have polynomial bounds on the resources required to achieve near-optimal return in general Markov decisio...