2011 search results - page 144 / 403 » Universal Reinforcement Learning |
139
click to vote
ALT
2007
Springer
15 years 10 months ago
2007
Springer
In transfer learning the aim is to solve new learning tasks using fewer examples by using information gained from solving related tasks. Existing transfer learning methods have be...
120
Voted
ATAL
2006
Springer
15 years 8 months ago
2006
Springer
Coordinating agents in a complex environment is a hard problem, but it can become even harder when certain characteristics of the tasks, like the required number of agents, are un...
141
click to vote
AAAI
1994
15 years 5 months ago
1994
Researchers in the eld of Distributed Arti cial Intelligence (DAI) have been developing e cient mechanisms to coordinate the activities of multiple autonomous agents. The need for...
183
click to vote
ECML
2006
Springer
15 years 8 months ago
2006
Springer
We target the problem of closed-loop learning of control policies that map visual percepts to continuous actions. Our algorithm, called Reinforcement Learning of Joint Classes (RLJ...
142
click to vote
NIPS
2007
15 years 5 months ago
2007
We present four new reinforcement learning algorithms based on actor-critic and natural-gradient ideas, and provide their convergence proofs. Actor-critic reinforcement learning m...