499 search results - page 26 / 100 » Model Minimization in Markov Decision Processes |
ICASSP
2009
IEEE
14 years 3 months ago
2009
IEEE
Semi-continuous acoustic models, where the output distributions for all Hidden Markov Model states share a common codebook of Gaussian density functions, are a well-known and prov...
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
2007
Springer
14 years 21 days ago
2007
Springer
This paper extends the framework of dynamic influence diagrams (DIDs) to the multi-agent setting. DIDs are computational representations of the Partially Observable Markov Decisio...
CORR
2010
Springer
13 years 7 months ago
2010
Springer
We consider model-based reinforcement learning in finite Markov Decision Processes (MDPs), focussing on so-called optimistic strategies. Optimism is usually implemented by carryin...
AAAI
2010
13 years 10 months ago
2010
Automatically constructing novel representations of tasks from analysis of state spaces is a longstanding fundamental challenge in AI. I review recent progress on this problem for...