155 search results - page 6 / 31 » Multi-agent Reinforcement Learning Using Strategies and Voti... |
113
click to vote
TSMC
2008
15 years 1 months ago
2008
This paper describes several ensemble methods that combine multiple different reinforcement learning (RL) algorithms in a single agent. The aim is to enhance learning speed and fin...
116
click to vote
NAACL
2001
15 years 2 months ago
2001
Developing dialogue systems is a complex process. In particular, designing efficient dialogue management strategies is often difficult as there are no precise guidelines to develo...
112
Voted
ICML
2005
IEEE
16 years 2 months ago
2005
IEEE
This paper describes the use of machine learning to improve the performance of natural language question answering systems. We present a model for improving story comprehension th...
140
click to vote
WSC
2007
15 years 3 months ago
2007
Adaptive Time Warp protocols in the literature are usually based on a pre-defined analytic model of the system, expressed as a closed form function that maps system state to cont...
105
click to vote
EWCBR
2008
Springer
15 years 3 months ago
2008
Springer
This paper presents CBRetaliate, an agent that combines Case-Based Reasoning (CBR) and Reinforcement Learning (RL) algorithms. Unlike most previous work where RL is used to improve...