86 search results - page 14 / 18 » Evolution of reward functions for reinforcement learning |
107
click to vote
GECCO
2009
Springer
15 years 4 months ago
2009
Springer
We apply CMA-ES, an evolution strategy with covariance matrix adaptation, and TDL (Temporal Difference Learning) to reinforcement learning tasks. In both cases these algorithms se...
ML
1998
ACM
14 years 11 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...
ATAL
2008
Springer
15 years 1 months ago
2008
Springer
In reinforcement learning, least-squares temporal difference methods (e.g., LSTD and LSPI) are effective, data-efficient techniques for policy evaluation and control with linear v...
123
click to vote
ICML
2000
IEEE
16 years 15 days ago
2000
IEEE
Eligibility traces have been shown to speed reinforcement learning, to make it more robust to hidden states, and to provide a link between Monte Carlo and temporal-difference meth...
111
click to vote
AGENTS
1999
Springer
15 years 4 months ago
1999
Springer
We consider the problem of how to design large decentralized multiagent systems (MAS’s) in an automated fashion, with little or no hand-tuning. Our approach has each agent run a...