238 search results - page 9 / 48 » Value-Function Approximations for Partially Observable Marko... |
COLT
2000
Springer
15 years 4 months ago
2000
Springer
We model reinforcement learning as the problem of learning to control a Partially Observable Markov Decision Process ( ¢¡¤£¦¥§ ), and focus on gradient ascent approache...
114
click to vote
NIPS
2007
15 years 1 months ago
2007
Bayesian Reinforcement Learning has generated substantial interest recently, as it provides an elegant solution to the exploration-exploitation trade-off in reinforcement learning...
111
click to vote
AMAI
2004
Springer
15 years 5 months ago
2004
Springer
This paper extends the framework of partially observable Markov decision processes (POMDPs) to multi-agent settings by incorporating the notion of agent models into the state spac...
109
click to vote
ICML
1999
IEEE
16 years 13 days ago
1999
IEEE
We present a learning algorithm for non-parametric hidden Markov models with continuous state and observation spaces. All necessary probability densities are approximated using sa...
NIPS
2004
15 years 1 months ago
2004
Existing algorithms for discrete partially observable Markov decision processes can at best solve problems of a few thousand states due to two important sources of intractability:...