4446 search results - page 442 / 890 » Learning Observer Agents |
153
click to vote
ICONIP
2009
15 years 4 months ago
2009
Reinforcement learning induces non-stationarity at several levels. Adaptation to non-stationary environments is of course a desired feature of a fair RL algorithm. Yet, even if the...
165
Voted
ICML
2006
IEEE
16 years 7 months ago
2006
IEEE
When the transition probabilities and rewards of a Markov Decision Process are specified exactly, the problem can be solved without any interaction with the environment. When no s...
208
click to vote
AIED
2005
Springer
16 years 12 days ago
2005
Springer
Our goal in this work has been to bring together the entertaining and flow characteristics of video game environments with proven learning theories to advance the state of the art ...
187
click to vote
EURONGI
2005
Springer
16 years 12 days ago
2005
Springer
We deploy a novel Reinforcement Learning optimization technique based on afterstates learning to determine the gain that can be achieved by incorporating movement prediction inform...
170
Voted
IDEAL
2004
Springer
16 years 7 days ago
2004
Springer
Abstract. Multiple classifier systems based on neural networks can give improved generalisation performance as compared with single classifier systems. We examine collaboration in ...