166 search results - page 11 / 34 » Online model learning in adversarial Markov decision process... |
156
click to vote
Publication
We introduce a class of learning problems where the agent is presented with a series of tasks. Intuitively, if there is relation among those tasks, then the information gained duri...
ATAL
2005
Springer
15 years 3 months ago
2005
Springer
Mediation is the process of decomposing a task into subtasks, finding agents suitable for these subtasks and negotiating with agents to obtain commitments to execute these subtas...
EMMCVPR
2001
Springer
15 years 2 months ago
2001
Springer
To segregate overlapping objects into depth layers requires the integration of local occlusion cues distributed over the entire image into a global percept. We propose to model thi...
ICML
2004
IEEE
15 years 10 months ago
2004
IEEE
Predictive state representations (PSRs) have recently been proposed as an alternative to partially observable Markov decision processes (POMDPs) for representing the state of a dy...
SOFSEM
2010
Springer
15 years 6 months ago
2010
Springer
Regret minimization has proven to be a very powerful tool in both computational learning theory and online algorithms. Regret minimization algorithms can guarantee, for a single de...