548 search results - page 14 / 110 » A New Way to Introduce Knowledge into Reinforcement Learning |
100
click to vote
AAAI
2006
14 years 11 months ago
2006
My research attempts to address on-line action selection in reinforcement learning from a Bayesian perspective. The idea is to develop more effective action selection techniques b...
103
click to vote
ECML
2007
Springer
14 years 11 months ago
2007
Springer
Many problems in areas such as Natural Language Processing, Information Retrieval, or Bioinformatic involve the generic task of sequence labeling. In many cases, the aim is to assi...
65
Voted
ICML
2010
IEEE
14 years 10 months ago
2010
IEEE
We introduce new, efficient algorithms for value iteration with multiple reward functions and continuous state. We also give an algorithm for finding the set of all nondominated a...
ATAL
2006
Springer
15 years 1 months ago
2006
Springer
We contribute Policy Reuse as a technique to improve a reinforcement learning agent with guidance from past learned similar policies. Our method relies on using the past policies ...
93
Voted
ISDA
2009
IEEE
15 years 4 months ago
2009
IEEE
This paper presents postponed updates, a new strategy for TD methods that can improve sample efficiency without incurring the computational and space requirements of model-based ...