Self-adjusting reinforcement learning

Research output: Contribution to journalArticlepeer-review


We present a variant of the Q-learning algorithm with automatic control of the exploration rate by a com- petition scheme. The theoretical approach is accom- panied by systematic simulations of a chaos control task. Finally, we give interpretations of the algorithm in the context of computational ecology and neural networks.
Original languageEnglish
Pages (from-to)441-444
Number of pages4
JournalNonlinear Theory and Its Applications (NOLTA)
Publication statusPublished - 1996


Dive into the research topics of 'Self-adjusting reinforcement learning'. Together they form a unique fingerprint.

Cite this