Travelled to:1 × Canada
1 × United Kingdom
2 × USA
Collaborated with:∅ D.Silver J.O.Kephart M.Sridharan
Talks about:learn (4) backgammon (2) connectionist (1) strategi (1) pricebot (1) competit (1) regress (1) converg (1) tempor (1) pseudo (1)
Person: Gerald Tesauro
DBLP: Tesauro:Gerald
Contributed to:
2009200019921988Wrote 5 papers:
- ICML-2009-SilverT #monte carlo #simulation
- Monte-Carlo simulation balancing (DS, GT), pp. 945–952.
- ICML-2000-KephartT #pseudo
- Pseudo-convergent Q-Learning by Competitive Pricebots (JOK, GT), pp. 463–470.
- ICML-2000-SridharanT #automation #multi
- Multi-agent Q-learning and Regression Trees for Automated Pricing Decisions (MS, GT), pp. 927–934.
- ML-1992-Tesauro #difference #learning
- Temporal Difference Learning of Backgammon Strategy (GT), pp. 451–457.
- ML-1988-Tesauro #learning
- Connectionist Learning of Expert Backgammon Evaluations (GT), pp. 200–206.