204 search results - page 21 / 41 » Stochastic Games |
IAT
2008
IEEE
14 years 1 months ago
2008
IEEE
This paper extends the link between evolutionary game theory and multi-agent reinforcement learning to multistate games. In previous work, we introduced piecewise replicator dynam...
QOFIS
2004
Springer
14 years 3 days ago
2004
Springer
Pricing is considered a relevant way to control congestion and differentiate services in communication networks. Among all pricing schemes, auctioning for bandwidth has received a...
ACG
2006
Springer
14 years 22 days ago
2006
Springer
Most game programs have a large number of parameters that are crucial for their performance. Tuning these parameters by hand is rather difficult. Therefore automatic optimization a...
NIPS
2001
13 years 8 months ago
2001
We consider the problem of learning to attain multiple goals in a dynamic environment, which is initially unknown. In addition, the environment may contain arbitrarily varying ele...
IJCAI
2001
13 years 8 months ago
2001
R-max is a very simple model-based reinforcement learning algorithm which can attain near-optimal average reward in polynomial time. In R-max, the agent always maintains a complet...