548 search results - page 13 / 110 » A New Way to Introduce Knowledge into Reinforcement Learning |
PKDD
2009
Springer
15 years 4 months ago
2009
Springer
Abstract. The Factored Markov Decision Process (FMDP) framework is a standard representation for sequential decision problems under uncertainty where the state is represented as a ...
71
Voted
ECIS
2001
14 years 11 months ago
2001
There is a growing sense that knowledge management, to be most effective, must address questions of knowledge creation and innovation in organisational contexts. Therefore, knowle...
75
Voted
NORDICHI
2004
ACM
15 years 2 months ago
2004
ACM
Mission Queen Maud Land (MQML) is a collaborative virtual environment that was developed to explore new ways to stimulate secondary school pupils to collaborate in grasping comple...
106
click to vote
ECML
2007
Springer
15 years 1 months ago
2007
Springer
Abstract. We present a new reinforcement learning approach for deterministic continuous control problems in environments with unknown, arbitrary reward functions. The difficulty of...
90
Voted
EPIA
2007
Springer
15 years 3 months ago
2007
Springer
Abstract. When a robot learns to solve a goal-directed navigation task with reinforcement learning, the acquired strategy can usually exclusively be applied to the task that has be...