The SCEAS System
Navigation Menu

Search the dblp DataBase

Title:
Author:

Istvan Szita: [Publications] [Author Rank by year] [Co-authors] [Prefers] [Cites] [Cited by]

Publications of Author

  1. Istvan Szita, Bálint Takács, András Lörincz
    Reinforcement Learning Integrated with a Non-Markovian Controller. [Citation Graph (0, 0)][DBLP]
    ECAI, 2002, pp:365-369 [Conf]
  2. Istvan Szita, Viktor Gyenes, András Lörincz
    Reinforcement Learning with Echo State Networks. [Citation Graph (0, 0)][DBLP]
    ICANN (1), 2006, pp:830-839 [Conf]
  3. Istvan Szita, Bálint Takács, András Lörincz
    Searching for Plannable Domains can Speed up Reinforcement Learning [Citation Graph (0, 0)][DBLP]
    CoRR, 2002, v:0, n:, pp:- [Journal]
  4. Bálint Takács, Istvan Szita, András Lörincz
    Temporal plannability by variance of the episode length [Citation Graph (0, 0)][DBLP]
    CoRR, 2003, v:0, n:, pp:- [Journal]
  5. Istvan Szita, András Lörincz
    Applying Policy Iteration for Training Recurrent Neural Networks [Citation Graph (0, 0)][DBLP]
    CoRR, 2004, v:0, n:, pp:- [Journal]
  6. Istvan Szita, András Lörincz
    Kalman filter control in the reinforcement learning framework [Citation Graph (0, 0)][DBLP]
    CoRR, 2003, v:0, n:, pp:- [Journal]
  7. Istvan Szita, András Lörincz
    Reinforcement Learning with Linear Function Approximation and LQ control Converges [Citation Graph (0, 0)][DBLP]
    CoRR, 2003, v:0, n:, pp:- [Journal]
  8. Istvan Szita, Bálint Takács, András Lörincz
    MDPs: Learning in Varying Environments. [Citation Graph (0, 0)][DBLP]
    Journal of Machine Learning Research, 2002, v:3, n:, pp:145-174 [Journal]
  9. Istvan Szita, András Lörincz
    Kalman Filter Control Embedded into the Reinforcement Learning Framework. [Citation Graph (0, 0)][DBLP]
    Neural Computation, 2004, v:16, n:3, pp:491-499 [Journal]
  10. Istvan Szita, András Lörincz
    Learning Tetris Using the Noisy Cross-Entropy Method. [Citation Graph (0, 0)][DBLP]
    Neural Computation, 2006, v:18, n:12, pp:2936-2941 [Journal]
  11. Istvan Szita, András Lörincz
    Low-complexity modular policies: learning to play Pac-Man and a new framework beyond MDPs [Citation Graph (0, 0)][DBLP]
    CoRR, 2006, v:0, n:, pp:- [Journal]

  12. Monte-Carlo Tree Search in Settlers of Catan. [Citation Graph (, )][DBLP]


  13. The many faces of optimism: a unifying approach. [Citation Graph (, )][DBLP]


  14. Optimistic initialization and greediness lead to polynomial time learning in factored MDPs. [Citation Graph (, )][DBLP]


  15. Model-based reinforcement learning with nearly tight exploration complexity bounds. [Citation Graph (, )][DBLP]


  16. Monte-Carlo Tree Search: A New Framework for Game AI. [Citation Graph (, )][DBLP]


  17. Factored Value Iteration Converges. [Citation Graph (, )][DBLP]


  18. Online variants of the cross-entropy method [Citation Graph (, )][DBLP]


  19. Factored Value Iteration Converges [Citation Graph (, )][DBLP]


  20. The many faces of optimism - Extended version [Citation Graph (, )][DBLP]


  21. Optimistic Initialization and Greediness Lead to Polynomial Time Learning in Factored MDPs - Extended Version [Citation Graph (, )][DBLP]


Search in 0.003secs, Finished in 0.004secs
NOTICE1
System may not be available sometimes or not working properly, since it is still in development with continuous upgrades
NOTICE2
The rankings that are presented on this page should NOT be considered as formal since the citation info is incomplete in DBLP
 
System created by asidirop@csd.auth.gr [http://users.auth.gr/~asidirop/] © 2002
for Data Engineering Laboratory, Department of Informatics, Aristotle University © 2002