502 search results - page 59 / 101 » Monotone Approximation of Decision Problems |
ATAL
2006
Springer
15 years 1 months ago
2006
Springer
Decentralized partially observable Markov decision processes (DEC-POMDPs) form a general framework for planning for groups of cooperating agents that inhabit a stochastic and part...
CORR
2010
Springer
14 years 9 months ago
2010
Springer
Temporal difference methods are theoretically grounded and empirically effective methods for addressing reinforcement learning problems. In most real-world reinforcement learning ...
ICML
2007
IEEE
15 years 10 months ago
2007
IEEE
This paper investigates the problem of automatically learning how to restructure the reward function of a Markov decision process so as to speed up reinforcement learning. We begi...
129
click to vote
EC
2011
14 years 4 months ago
2011
Abstract—In the field of evolutionary multi-criterion optimization, the hypervolume indicator is the only single set quality measure that is known to be strictly monotonic with ...
ECCC
2006
14 years 9 months ago
2006
Attempts at classifying computational problems as polynomial time solvable, NP-complete, or belonging to a higher level in the polynomial hierarchy, face the difficulty of undecid...