128 search results - page 20 / 26 » Hierarchically Optimal Average Reward Reinforcement Learning |
COLT
2007
Springer
14 years 1 months ago
2007
Springer
Abstract. We propose simple randomized strategies for sequential prediction under imperfect monitoring, that is, when the forecaster does not have access to the past outcomes but r...
AGENTS
1999
Springer
13 years 12 months 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...
SIAMCO
2000
13 years 7 months ago
2000
It is shown here that stability of the stochastic approximation algorithm is implied by the asymptotic stability of the origin for an associated ODE. This in turn implies convergen...
GECCO
2005
Springer
14 years 1 months ago
2005
Springer
Recurrent neural networks are theoretically capable of learning complex temporal sequences, but training them through gradient-descent is too slow and unstable for practical use i...
ATAL
2010
Springer
13 years 7 months ago
2010
Springer
PAC-MDP algorithms approach the exploration-exploitation problem of reinforcement learning agents in an effective way which guarantees that with high probability, the algorithm pe...