Szepesvári C, Lörincz A.  1993.  Behavior of an Adaptive Self-organizing Autonomous Agent Working with Cues and Competing Concepts. Adaptive Behaviour. 2:131–160.

Szepesvári C, Lörincz A.  1996.  Approximate geometry representations and sensory fusion. Neurocomputing. 12:267–287.

Littman ML, Szepesvári C.  1996.  A Generalized Reinforcement-Learning Model: Convergence and Applications. ICML. :310–318.

Fomin T, Rozgonyi T, Szepesvári C, Lörincz A.  1996.  Self-Organizing Multi-Resolution Grid for Motion Planning and Control. Int. J. Neural Syst.. 7:757.

Szepesvári C.  1997.  The Asymptotic Convergence-Rate of Q-learning. NIPS. :1064–1070.

Szepesvári C.  1997.  Learning and Exploitation Do Not Conflict Under Minimax Optimality. ECML. 1224:242–249.

Szepesvári C, Cimmer S, Lörincz A.  1997.  Neurocontroller using dynamic state feedback for compensatory control. Neural Networks. 10:1691–1708.

Kalmár Z, Szepesvári C, Lörincz A.  1998.  Module-Based Reinforcement Learning: Experiments with a Real Robot. Machine Learning. 31:55–85.

Szepesvári C.  1998.  Non-Markovian Policies in Sequential Decision Problems. Acta Cybern.. 13:305-318.