86 search results - page 15 / 18 » Evolution of reward functions for reinforcement learning |
ICML
2010
IEEE
15 years 23 days ago
2010
IEEE
This paper formalizes Feature Selection as a Reinforcement Learning problem, leading to a provably optimal though intractable selection policy. As a second contribution, this pape...
116
click to vote
IEEEPACT
2008
IEEE
15 years 6 months ago
2008
IEEE
Communication overheads are one of the fundamental challenges in a multiprocessor system. As the number of processors on a chip increases, communication overheads and the distribu...
ML
1998
ACM
14 years 11 months ago
1998
ACM
We use simulated soccer to study multiagent learning. Each team's players (agents) share action set and policy, but may behave di erently due to position-dependent inputs. All...
102
click to vote
ICRA
2010
IEEE
14 years 10 months ago
2010
IEEE
Multi-robot systems researchers have been investigating adaptive coordination methods for improving spatial coordination in teams. Such methods adapt the coordination method to th...
GECCO
2004
Springer
15 years 5 months ago
2004
Springer
A new graph-based evolutionary algorithm named “Genetic Network Programming, GNP” has been proposed. GNP represents its solutions as directed graph structures, which can improv...