1227 search results - page 1 / 246 » Learning Rates for Q-Learning |
IROS
2008
IEEE
14 years 1 months ago
2008
IEEE
—Multi-robot reinforcement learning is a very challenging area due to several issues, such as large state spaces, difficulty in reward assignment, nondeterministic action selecti...
ICML
1998
IEEE
14 years 8 months ago
1998
IEEE
This paper presents a new approach to hierarchical reinforcement learning based on the MAXQ decomposition of the value function. The MAXQ decomposition has both a procedural seman...
NIPS
2003
13 years 8 months ago
2003
Recent multi-agent extensions of Q-Learning require knowledge of other agents’ payoffs and Q-functions, and assume game-theoretic play at all times by all other agents. This pap...
ICRA
2002
IEEE
14 years 11 days ago
2002
IEEE
Learning can be an effective way for robot systems to deal with dynamic environments and changing task conditions. However, popular singlerobot learning algorithms based on discou...
AAAI
2012
11 years 9 months ago
2012
To solve the sparsity problem in collaborative filtering, researchers have introduced transfer learning as a viable approach to make use of auxiliary data. Most previous transfer...