Sciweavers

ML
1998
ACM
136views Machine Learning» more  ML 1998»
13 years 10 months ago
Co-Evolution in the Successful Learning of Backgammon Strategy
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...
Jordan B. Pollack, Alan D. Blair
NIPS
1996
14 years 6 days ago
Why did TD-Gammon Work?
Although TD-Gammon is one of the major successes in machine learning, it has not led to similar impressive breakthroughs in temporal difference learning for other applications or ...
Jordan B. Pollack, Alan D. Blair
FLAIRS
2003
14 years 8 days ago
Learning Opening Strategy in the Game of Go
In this paper, we present an experimental methodology and results for a machine learning approach to learning opening strategy in the game of Go, a game for which the best compute...
Timothy Huang, Graeme Connell, Bryan McQuade
NIPS
2007
14 years 9 days ago
Incremental Natural Actor-Critic Algorithms
We present four new reinforcement learning algorithms based on actor-critic and natural-gradient ideas, and provide their convergence proofs. Actor-critic reinforcement learning m...
Shalabh Bhatnagar, Richard S. Sutton, Mohammad Gha...
NIPS
2008
14 years 9 days ago
On the asymptotic equivalence between differential Hebbian and temporal difference learning using a local third factor
In this theoretical contribution we provide mathematical proof that two of the most important classes of network learning - correlation-based differential Hebbian learning and rew...
Christoph Kolodziejski, Bernd Porr, Minija Tamosiu...
CG
2000
Springer
14 years 3 months ago
Chess Neighborhoods, Function Combination, and Reinforcement Learning
Abstract. Over the years, various research projects have attempted to develop a chess program that learns to play well given little prior knowledge beyond the rules of the game. Ea...
Robert Levinson, Ryan Weber
GECCO
2009
Springer
124views Optimization» more  GECCO 2009»
14 years 3 months ago
Reinforcement learning for games: failures and successes
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...
Wolfgang Konen, Thomas Bartz-Beielstein
CIG
2006
IEEE
14 years 5 months ago
Temporal Difference Learning Versus Co-Evolution for Acquiring Othello Position Evaluation
Abstract— This paper compares the use of temporal difference learning (TDL) versus co-evolutionary learning (CEL) for acquiring position evaluation functions for the game of Othe...
Simon M. Lucas, Thomas Philip Runarsson