252 search results - page 25 / 51 » Learning Partially Observable Action Models: Efficient Algor... |
163
Voted
ACL
2010
15 years 19 days ago
2010
Open-ended spoken interactions are typically characterised by both structural complexity and high levels of uncertainty, making dialogue management in such settings a particularly...
134
click to vote
ICML
2006
IEEE
16 years 3 months ago
2006
IEEE
Reinforcement learning (RL) was originally proposed as a framework to allow agents to learn in an online fashion as they interact with their environment. Existing RL algorithms co...
131
Voted
NIPS
2001
15 years 4 months ago
2001
We show that states of a dynamical system can be usefully represented by multi-step, action-conditional predictions of future observations. State representations that are grounded...
107
Voted
ECML
2006
Springer
15 years 6 months ago
2006
Springer
The standard approach for learning Markov Models with Hidden State uses the Expectation-Maximization framework. While this approach had a significant impact on several practical ap...
109
Voted
JMLR
2010
14 years 9 months ago
2010
Logic-based probabilistic models (LBPMs) enable us to handle problems with uncertainty succinctly thanks to the expressive power of logic. However, most of LBPMs have restrictions...