1234 search results - page 50 / 247 » Multi-criteria Reinforcement Learning |
138
click to vote
ICML
2004
IEEE
16 years 4 months ago
2004
IEEE
lative Novelty to Identify Useful Temporal Abstractions in Reinforcement Learning ?Ozg?ur S?im?sek ozgur@cs.umass.edu Andrew G. Barto barto@cs.umass.edu Department of Computer Scie...
135
Voted
ECML
2006
Springer
15 years 7 months ago
2006
Springer
Reinforcement learning in real-world domains suffers from three curses of dimensionality: explosions in state and action spaces, and high stochasticity. We present approaches that ...
131
click to vote
ML
1998
ACM
15 years 3 months ago
1998
ACM
Following Tesauro’s work on TD-Gammon, we used a 4000 parameter feed-forward neural network to develop a competitive backgammon evaluation function. Play proceeds by a roll of t...
156
click to vote
MAGS
2010
14 years 10 months ago
2010
Coordinating agents in a complex environment is a hard problem, but it can become even harder when certain characteristics of the tasks, like the required number of agents, are un...
117
click to vote
PRIMA
2009
Springer
15 years 10 months ago
2009
Springer
In this article, we propose a method to adapt stepsize parameters used in reinforcement learning for dynamic environments. In general reinforcement learning situations, a stepsize...