3 search results - page 1 / 1 » Thresholded Rewards: Acting Optimally in Timed, Zero-Sum Gam... |
106
Voted
AAAI
2007
15 years 18 days ago
2007
In timed, zero-sum games, the goal is to maximize the probability of winning, which is not necessarily the same as maximizing our expected reward. We consider cumulative intermedi...
93
Voted
IJCAI
2001
14 years 11 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...
94
Voted
INFOCOM
2006
IEEE
15 years 4 months ago
2006
IEEE
— In autonomous mobile ad hoc networks (MANET) where each user is its own authority, fully cooperative behaviors, such as unconditionally forwarding packets for each other or, ho...