548 search results - page 9 / 110 » A New Way to Introduce Knowledge into Reinforcement Learning |
IJCAI
2003
14 years 11 months ago
2003
In multiagent environments, forms of social learning such as teaching and imitation have been shown to aid the transfer of knowledge from experts to learners in reinforcement lear...
HICSS
2008
IEEE
15 years 4 months ago
2008
IEEE
The US Military’s ability to meet its mission critical requirements calls for increased agility in its information technology development process. The purpose of this case study...
ICANN
2010
Springer
14 years 10 months ago
2010
Springer
We propose a new approach for reinforcement learning in problems with continuous actions. Actions are sampled by means of a diffusion tree, which generates samples in the continuou...
ICML
2008
IEEE
15 years 10 months ago
2008
IEEE
Rich representations in reinforcement learning have been studied for the purpose of enabling generalization and making learning feasible in large state spaces. We introduce Object...
ATAL
2010
Springer
14 years 9 months ago
2010
Springer
PAC-MDP algorithms approach the exploration-exploitation problem of reinforcement learning agents in an effective way which guarantees that with high probability, the algorithm pe...