István Szita

According to our database, István Szita authored at least 29 papers between 2002 and 2012.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2012

Reinforcement Learning in Games.

István Szita

Proceedings of the Reinforcement Learning, 2012

2011

Agnostic KWIK learning and efficient approximate reinforcement learning.

István Szita, Csaba Szepesvári

Proceedings of the COLT 2011, 2011

2010

Model-based reinforcement learning with nearly tight exploration complexity bounds.

Istvan Szita, Csaba Szepesvári

Proceedings of the 27th International Conference on Machine Learning (ICML-10), 2010

2009

Effective and Diverse Adaptive Game AI.

Istvan Szita, Marc J. V. Ponsen, Pieter Spronck

IEEE Trans. Comput. Intell. AI Games, 2009

Optimistic Initialization and Greediness Lead to Polynomial Time Learning in Factored MDPs - Extended Version

Istvan Szita, András Lörincz

CoRR, 2009

Exploring compact reinforcement-learning representations with linear regression.

Thomas J. Walsh, Istvan Szita, Carlos Diuk, Michael L. Littman

Proceedings of the UAI 2009, 2009

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

Istvan Szita, András Lörincz

Proceedings of the 26th Annual International Conference on Machine Learning, 2009

Monte-Carlo Tree Search in Settlers of Catan.

Istvan Szita, Guillaume Chaslot, Pieter Spronck

Proceedings of the Advances in Computer Games, 12th International Conference, 2009

2008

Megerősítéses tanulás komplex környezetekben

István Szita

PhD thesis, 2008

Cross-Entropy for Monte-Carlo Tree Search.

Guillaume Chaslot, Mark H. M. Winands, Istvan Szita, H. Jaap van den Herik

J. Int. Comput. Games Assoc., 2008

The many faces of optimism - Extended version

Istvan Szita, András Lörincz

CoRR, 2008

Online variants of the cross-entropy method

Istvan Szita, András Lörincz

CoRR, 2008

Factored Value Iteration Converges.

Istvan Szita, András Lörincz

Acta Cybern., 2008

The many faces of optimism: a unifying approach.

Istvan Szita, András Lörincz

Proceedings of the Machine Learning, 2008

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

Guillaume Chaslot, Sander Bakkes, Istvan Szita, Pieter Spronck

Proceedings of the Fourth Artificial Intelligence and Interactive Digital Entertainment Conference, 2008

2007

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

Istvan Szita, András Lörincz

J. Artif. Intell. Res., 2007

2006

Learning Tetris Using the Noisy Cross-Entropy Method.

Istvan Szita, András Lörincz

Neural Comput., 2006

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

István Szita, András Lörincz

Neurocomputing, 2006

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

Istvan Szita, András Lörincz

CoRR, 2006

Reinforcement Learning with Echo State Networks.

Istvan Szita, Viktor Gyenes, András Lörincz

Proceedings of the Artificial Neural Networks, 2006

2004

Kalman Filter Control Embedded into the Reinforcement Learning Framework.

Istvan Szita, András Lörincz

Neural Comput., 2004

Applying Policy Iteration for Training Recurrent Neural Networks

Istvan Szita, András Lörincz

CoRR, 2004

2003

Reinforcement Learning with Linear Function Approximation and LQ control Converges

Istvan Szita, András Lörincz

CoRR, 2003

Kalman filter control in the reinforcement learning framework

Istvan Szita, András Lörincz

CoRR, 2003

Temporal plannability by variance of the episode length

Bálint Takács, Istvan Szita, András Lörincz

CoRR, 2003

Event-learning and robust policy heuristics.

András Lörincz, Imre Pólik, Istvan Szita

Cogn. Syst. Res., 2003

2002

MDPs: Learning in Varying Environments.

Istvan Szita, Bálint Takács, András Lörincz

J. Mach. Learn. Res., 2002

Searching for Plannable Domains can Speed up Reinforcement Learning

Istvan Szita, Bálint Takács, András Lörincz

CoRR, 2002

Reinforcement Learning Integrated with a Non-Markovian Controller.

Istvan Szita, Bálint Takács, András Lörincz

Proceedings of the 15th European Conference on Artificial Intelligence, 2002