13376 search results - page 2408 / 2676 » Problem Solving with |
109
click to vote
NIPS
2003
15 years 5 months ago
2003
We study an approach to policy selection for large relational Markov Decision Processes (MDPs). We consider a variant of approximate policy iteration (API) that replaces the usual...
139
click to vote
UAI
2003
15 years 5 months ago
2003
This paper examines a number of solution methods for decision processes with non-Markovian rewards (NMRDPs). They all exploit a temporal logic specification of the reward functio...
121
Voted
EACL
1993
ACL Anthology
15 years 5 months ago
1993
ACL Anthology
The first part of the paper develops a novel, sortally-based approach to the problem of aspectual composition. The account is argued to be superior on both empirical and computati...
143
click to vote
NIPS
1993
15 years 5 months ago
1993
While exploring to nd better solutions, an agent performing online reinforcement learning (RL) can perform worse than is acceptable. In some cases, exploration might have unsafe, ...
116
click to vote
IJCAI
1989
15 years 5 months ago
1989
A modest exception allowing inheritance reasoner is presented. The reasoner allows restricted, but semantically well founded, defeasible property inheritance. Furthermore, it give...