4544 search results - page 153 / 909 » Reinforcement Learning with Time |
218
click to vote
ECML
2006
Springer
15 years 10 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...
172
click to vote
NIPS
2007
15 years 8 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...
174
click to vote
NIPS
1993
15 years 7 months ago
1993
Dynamic programming provides a methodology to develop planners and controllers for nonlinear systems. However, general dynamic programming is computationally intractable. We have ...
135
click to vote
ICML
2006
IEEE
16 years 7 months ago
2006
IEEE
We introduce relational temporal difference learning as an effective approach to solving multi-agent Markov decision problems with large state spaces. Our algorithm uses temporal ...
146
click to vote
ICCBR
2009
Springer
16 years 1 months ago
2009
Springer
Positive transfer learning (TL) occurs when, after gaining experience from learning how to solve a (source) task, the same learner can exploit this experience to improve performanc...