This page lists my publications, most of which are available for download and some have been converted to HTML for browsing. Please report any problems with downloading, previewing, or printing them. I can send hardcopies on request.

Theses

1. Cichosz, P. (1997). Reinforcement Learning by Truncating Temporal Differences. PhD Thesis, Department of Electronics and Information Technology, Warsaw University of Technology.
   Read the abstract, download gzipped postscipt (1,591,305 bytes, 242 pages).
   
2. Cichosz, P. (1994). Reinforcement Learning Algorithms Based on the Methods of Temporal Differences. Master's Thesis, Institute of Computer Science, Warsaw University of Technology.
   Read the abstract, download gzipped postscipt (376,887 bytes, 152 pages).
   

International Journals

1. Cichosz, P. (2011). Assessing the quality of classification models: Performance measures and evaluation procedures. Central European Journal of Engineering, 1:132-158.
   View on SpringerLink.
2. Cichosz, P. (2000). A forwards view of replacing eligibility traces for states and state-action pairs. Mathematical Algorithms, 1:283-297.
   Read the abstract, download gzipped postscipt (78,463 bytes, 22 pages).
3. Cichosz, P. (1999). An analysis of experience replay in temporal difference learning. Cybernetics and Systems, 30:341-363.
   Read the abstract, download gzipped postscipt (101,770 bytes, 23 pages).
4. Cichosz, P. (1999). TD(λ) learning without eligibility traces: A theoretical analysis. Journal of Experimental and Theoretical Artificial Intelligence, 11:239-263.
   Read the abstract, download gzipped postscipt (122,280 bytes, 30 pages).
5. Cichosz, P. (1996). Delayed reinforcement learning of multidimensional control actions. Systems Analysis-Modelling-Simulation, 24:233-248.
   Read the abstract.
6. Cichosz, P. (1995). Truncating temporal differences: On the efficient implementation of TD(λ) for reinforcement learning. Journal of Artificial Intelligence Research, 2:287-318.
   Read the abstract, download gzipped postscipt (108,231 bytes, 32 pages), browse HTML.
   
   

Polish Journals

1. Cichosz, P. (1995). Wprowadzenie do systemow uczacych sie ze wzmocnieniem. Informatyka, 4/96.
   

International Conferences

1. Wawrzynski, P., Arabas, J., & Cichosz, P. (2008). Predictive control for Artificial Intelligence in computer games. In Proceedings of the Tenth International Conference on Artificial Intelligence and Soft Computing (ICAISC-2008). Springer. Read the abstract, view PDF.
   
   
2. Arabas, J. & Cichosz, P. (2006). Search-based view of Artificial Intelligence. In Artificial Intelligence Studies, Academy of Podlasie.
3. Walczak, T. & Cichosz, P. (2006). A distributed learning control system for elevator groups. In Proceedings of the Eighth International Conference on Artificial Intelligence and Soft Computing (ICAISC-2008). Springer. Read the abstract, view PDF.
   
   
4. Cichosz, P. (1997). Integrated learning and planning based on truncating temporal differences. In Proceedings of the Ninth European Conference on Machine Learning (ECML-97). Springer.
   Read the abstract, view PDF.
   
   
5. Cichosz, P. (1996). Truncated temporal differences with function approximation: Successful examples using CMAC. In Proceedings of the Thirteenth European Meeting on Cybernetics and Systems Research (EMCSR-96). Austrian Society for Cybernetic Studies.
   Read the abstract, download gzipped postscript (185,857 bytes, 6 pages), browse HTML.
   
   
6. Cichosz, P. (1996). Truncated temporal differences and sequential replay: Comparison, integration, and experiments. To appear in Proceedings of the Poster Session of the Ninth International Symposium on Methodologies for Intelligent Systems (ISMIS-96), Zakopane, Poland. Oak Ridge Laboratory.
   Read the abstract, download gzipped postscript (241,608 bytes, 15 pages).
   
   
7. Cichosz, P., & Mulawka, J. J. (1995). Fast and efficient reinforcement learning with truncated temporal differences. In Proceedings of the Twelfth International Conference on Machine Learning (ML-95), Tahoe City, California. Morgan Kaufmann.
   Read the abstract, download gzipped postscipt (62,179 bytes, 9 pages), browse HTML.
   
   
8. Cichosz, P., & Mulawka, J. J. (1995). Integrated architectures for learning, planning, and reacting based on approximating TD(λ). In Proceedings of the First International Workshop on Intelligent Adaptive Systems (IAS-95), Melbourne Beech, Florida.
   Read the abstract, download gzipped postscipt (47,968 bytes, 12 pages).
   
   
9. Cichosz, P., & Mulawka, J. J. (1995). GBQL: A novel genetics-based reinforcement learning architecture. In Proceedings of the Third European Congress on Intelligent Techniques and Soft Computing (EUFIT'95), Aachen, Germany.
   Read the abstract, download gzipped postscipt (40,508 bytes, 5 pages).
   
   
10. Cichosz, P. (1995). Learning multidimensional control actions from delayed reinforcements. In Proceedings of the Eighth International Symposium on System-Modelling-Control (SMC-8), Zakopane, Poland.
    Read the abstract, download gzipped postscipt (43,011 bytes, 6 pages).
    
    
11. Cichosz, P., & Mulawka, J. J. (1995). Towards more efficient intelligent agents learning from delayed rewards. In Proceedings of the IV International Workshop on Intelligent Information Systems (WIS'95), Augustow, Poland.
    
    
12. Seredynski, F., Cichosz, P., & Klebus, G. P. (1995). Learning classifier systems in multi-agent environments. In Proceedings of the First IEE/IEEE International Conference on Genetic Algorithms in Engineering Systems: Innovations and Applications (GALESIA'95), Sheffield, UK.
    Read the abstract, download gzipped postscipt (40,937 bytes, 6 pages).
    

Polish Conferences

1. Cichosz, P., & Mulawka, J. J. (1996). Faster temporal credit assignment in learning classifier systems. In Proceedings of the First Polish Conference on Evolutionary Algorithms (KAE-96), Murzasichle, Poland.
   Read the abstract, download gzipped postscript (47,017 bytes, 10 pages).
   
   
2. Cichosz, P., & Mulawka, J. J. (1995, in Polish). Uczenie sie sekwencyjnego podejmowania decyzji w oparciu o opoznione nagrody. Materialy Krajowej Konferencji: Analiza Decyzyjna, Systemy Ekspertowe, Zastosowania Systemow Komputerowych, IBS PAN, Warszawa, Polska.
   
   
3. Mulawka, J. J., & Cichosz, P. (1994, in Polish). Systemy uczace sie i perspektywy ich zastosowan w dziedzinie ekonomii. Materialy Konferencji INFOGRYF'94, Kolobrzeg, Polska.
   

Technical Reports

1. Seredynski, F., Cichosz, P., & Klebus, G. P. (1995, in Polish). (CS)LAG: system do symulacji gier uczacych sie agentow. Technical report 778, Institute of Computer Science, Polish Academy of Sciences.
   
   
2. Cichosz, P., Klebus, G. P. (1994). Visual presentation of inheritance structures: A case study in object oriented programming. Research report 8/94, Institute of Computer Science, Warsaw University of Technology.