548 search results - page 17 / 110 » A New Way to Introduce Knowledge into Reinforcement Learning |
116
click to vote
AAAI
2012
13 years 2 months ago
2012
Markov decision processes (MDPs) are an established framework for solving sequential decision-making problems under uncertainty. In this work, we propose a new method for batchmod...
104
click to vote
ISCA
2008
IEEE
15 years 6 months ago
2008
IEEE
Efficiently utilizing off-chip DRAM bandwidth is a critical issue in designing cost-effective, high-performance chip multiprocessors (CMPs). Conventional memory controllers deli...
KDD
2010
ACM
15 years 3 months ago
2010
ACM
In this paper, we propose and develop a novel approach to the problem of optimally managing the tax, and more generally debt, collections processes at financial institutions. Our...
AGENTS
1999
Springer
15 years 4 months ago
1999
Springer
In this paper, we present a novel multi-agent learning paradigm called team-partitioned, opaque-transition reinforcement learning (TPOT-RL). TPOT-RL introduces the concept of usin...
JMLR
2008
14 years 11 months ago
2008
A number of today's state-of-the-art planners are based on forward state-space search. The impressive performance can be attributed to progress in computing domain independen...