458 search results - page 43 / 92 » Q-Decomposition for Reinforcement Learning Agents |
CEC
2008
IEEE
13 years 11 months ago
2008
IEEE
Abstract-- In this paper we investigate the effects of individual learning on an evolving population of situated agents. We work with a novel type of system where agents can decide...
AAAI
2006
13 years 10 months ago
2006
Transfer learning concerns applying knowledge learned in one task (the source) to improve learning another related task (the target). In this paper, we use structure mapping, a ps...
ISDA
2009
IEEE
14 years 3 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 ...
CORR
2007
Springer
13 years 9 months ago
2007
Springer
—We consider an agent interacting with an unmodeled environment. At each time, the agent makes an observation, takes an action, and incurs a cost. Its actions can influence futu...
IJCNN
2006
IEEE
14 years 3 months ago
2006
IEEE
Abstract— Groups of reinforcement learning agents interacting in a common environment often fail to learn optimal behaviors. Poor performance is particularly common in environmen...