István Szita

发表

Low-complexity modular policies: learning to play Pac-Man and a new framework beyond MDPs pdf

András Lörincz, István Szita, I. Szita, 2006, ArXiv.

The many faces of optimism - Extended version pdf

András Lörincz, István Szita, 2008, ArXiv.

Event-learning and robust policy heuristics

András Lörincz, István Szita, Imre Pólik, 2003, Cognitive Systems Research.

Cross-Entropy for Monte-Carlo Tree Search

H. Jaap van den Herik, Mark H. M. Winands, Guillaume Chaslot, 2008, J. Int. Comput. Games Assoc..

Factored Value Iteration Converges pdf

András Lörincz, István Szita, 2008, Acta Cybern..

Monte-Carlo Tree Search in Settlers of Catan

Pieter Spronck, Guillaume Chaslot, István Szita, 2009, ACG.

The many faces of optimism: a unifying approach

András Lörincz, István Szita, I. Szita, 2008, ICML '08.

PIRANHA: Policy iteration for recurrent artificial neural networks with hidden activities

András Lörincz, István Szita, I. Szita, 2006, Neurocomputing.

Monte-Carlo Tree Search: A New Framework for Game AI

Pieter Spronck, Sander Bakkes, Guillaume Chaslot, 2008, AIIDE.

Kalman filter control in the reinforcement learning framework

András Lörincz, István Szita, I. Szita, 2003, ArXiv.

Searching for Plannable Domains can Speed up Reinforcement Learning

András Lörincz, Bálint Takács, István Szita, 2002, ArXiv.

Model-based reinforcement learning with nearly tight exploration complexity bounds

Csaba Szepesvári, István Szita, Csaba Szepesvari, 2010, ICML.

Erratum

András Lörincz, István Szita, 2007, Neural Computation.

MDPs: Learning in Varying Environments

András Lörincz, Bálint Takács, István Szita, 2003, J. Mach. Learn. Res..

Reinforcement Learning with Echo State Networks

András Lörincz, Viktor Gyenes, István Szita, 2006, ICANN.

Optimistic initialization and greediness lead to polynomial time learning in factored MDPs pdf

András Lörincz, István Szita, I. Szita, 2009, ICML '09.

Exploring compact reinforcement-learning representations with linear regression

Thomas J. Walsh, Michael L. Littman, Carlos Diuk, 2009, UAI.

Effective and Diverse Adaptive Game AI

Pieter Spronck, István Szita, Marc J. V. Ponsen, 2009, IEEE Transactions on Computational Intelligence and AI in Games.

Learning to Play Using Low-Complexity Rule-Based Policies: Illustrations through Ms. Pac-Man

András Lörincz, István Szita, I. Szita, 2007, J. Artif. Intell. Res..

Agnostic KWIK learning and efficient approximate reinforcement learning

Csaba Szepesvári, István Szita, Csaba Szepesvari, 2011, COLT.

Reinforcement Learning Integrated with a Non-Markovian Controller

András Lörincz, Bálint Takács, István Szita, 2002, ECAI.

Learning Tetris Using the Noisy Cross-Entropy Method

András Lörincz, István Szita, I. Szita, 2006, Neural Computation.

Reinforcement Learning with Linear Function Approximation and LQ control Converges

András Lörincz, István Szita, I. Szita, 2003, ArXiv.

Online variants of the cross-entropy method pdf

András Lörincz, István Szita, I. Szita, 2008, ArXiv.

Applying Policy Iteration for Training Recurrent Neural Networks

András Lörincz, István Szita, 2004, ArXiv.

Temporal plannability by variance of the episode length

András Lörincz, Bálint Takács, István Szita, 2003, ArXiv.