Search Results - subject:"Reinforcement Learning"

Can boundedly rational sellers learn to play Nash?

Waldeck, Roger; Darmon, Eric - In: Journal of Economic Interaction and Coordination 1 (2006) 2, pp. 147-169

Persistent link: https://www.econbiz.de/10005390641

Duopolistic competition in an electricity markets with heterogeneous cost functions

Guerci, Eric; Ivaldi, Stefano; Raberto, Marco; … - Society for Computational Economics - SCE - 2006

's decision-making process has been modeled according to different reinforcement learning algorithms, namely, Marimon and …

Persistent link: https://www.econbiz.de/10005706196

Interaction dynamics of two reinforcement learners

Gutjahr, Walter - In: Central European Journal of Operations Research 14 (2006) 1, pp. 59-86

Persistent link: https://www.econbiz.de/10008515680

ADAPTIVE HIGHLIGHTING OF LINKS TO ASSIST SURFING ON THE INTERNET

PALOTAI, ZSOLT; GÁBOR, BÁLINT; LŐRINCZ, ANDRÁS - In: International Journal of Information Technology & … 04 (2005) 01, pp. 117-139

Gathering of novel information from the WWW constitutes a real challenge for artificial intelligence (AI) methods. Large search engines do not offer a satisfactory solution, their indexing cycle is long and they may offer a huge amount of documents. An AI-based assistant agent is studied here,...

Persistent link: https://www.econbiz.de/10004971655

Reinforcement learning for congestion-avoidance in packet flow

Horiguchi, Tsuyoshi; Hayashi, Keisuke; Tretiakov, Alexei - In: Physica A: Statistical Mechanics and its Applications 349 (2005) 1, pp. 329-348

reinforcement learning for a control parameter in the neural network model. We find that the congestion is avoided by the … reinforcement learning and at the same time we have good performance for the throughput. We investigate the packet flow on computer …

Persistent link: https://www.econbiz.de/10010874595

HOW INDIVIDUALS LEARN TO TAKE TURNS: EMERGENCE OF ALTERNATING COOPERATION IN A CONGESTION GAME AND THE PRISONER'S DILEMMA

HELBING, DIRK; SCHÖNHOF, MARTIN; STARK, HANS-ULRICH; … - In: Advances in Complex Systems (ACS) 08 (2005) 01, pp. 87-116

can be explained with a novel reinforcement learning model for an arbitrary number of persons, which is based on past …

Persistent link: https://www.econbiz.de/10005080922

Games of Competition in a Stochastic Environment

Avrahami, Judith; Güth, Werner; Kareev, Yaakov - In: Theory and Decision 59 (2005) 4, pp. 255-294

playing repeatedly. Of the five benchmarksâ€”the unique (Nash) equilibrium, reinforcement learning, trust-based efficiency …

Persistent link: https://www.econbiz.de/10005709858

Individual and Social Learning

Hanaki, Nobuyuki - In: Computational Economics 26 (2005) 3, pp. 31-50

generate an efficient and fair outcome. Yet such typical learning models as Fictitious Play and Reinforcement Learning have …

Persistent link: https://www.econbiz.de/10005701788

Convergence of reinforcement learning to Nash equilibrium: A search-market experiment

Darmon, Eric; Waldeck, Roger - In: Physica A: Statistical Mechanics and its Applications 355 (2005) 1, pp. 119-130

Since the introduction of Reinforcement Learning (RL) in Game Theory, a growing literature is concerned with the …

Persistent link: https://www.econbiz.de/10010591758

Evidence for Learning to Learn Behavior in Normal Form Games

Salmon, Timothy - In: Theory and Decision 56 (2004) 4, pp. 367-404

Evidence presented in Salmon (2001; Econometrica 69(6) 1597) indicates that typical tests to identify learning behavior in experiments involving normal form games possess little power to reject incorrect models. This paper begins by presenting results from an experiment designed to gather...

Persistent link: https://www.econbiz.de/10005068018