473 search results - page 69 / 95 » Optimal policy switching algorithms for reinforcement learni... |
RSS
2007
13 years 9 months ago
2007
Abstract— This paper proposes a simulation-based active policy learning algorithm for finite-horizon, partially-observed sequential decision processes. The algorithm is tested i...
ML
2002
ACM
13 years 7 months ago
2002
ACM
An issue that is critical for the application of Markov decision processes MDPs to realistic problems is how the complexity of planning scales with the size of the MDP. In stochas...
AGENTS
1999
Springer
14 years 15 hour ago
1999
Springer
We consider the problem of how to design large decentralized multiagent systems (MAS’s) in an automated fashion, with little or no hand-tuning. Our approach has each agent run a...
NCA
2010
IEEE
13 years 6 months ago
2010
IEEE
The Support Vector Machine (SVM) is an interesting classifier with excellent power of generalization. In this paper, we consider applying the SVM to semi-supervised learning. We p...
EWRL
2008
13 years 9 months ago
2008
Abstract. We consider a control problem where the decision maker interacts with a standard Markov decision process with the exception that the reward functions vary arbitrarily ove...