Reducing state space exploration in reinforcement learning problems by rapid identification of initial solutions and progressive improvement of them

    Research output: Chapter in Book/Report/Conference proceedingChapterScientificpeer-review

    Original languageEnglish
    Title of host publicationAdvances in Neural Networks World
    EditorsA. Grmela, N.E. Mastorakis
    PublisherWSEAS Press
    Publication statusPublished - 2002
    MoE publication typeA3 Part of a book or another research book


    • Reinforcement learning, Trajectory sampling, Temporal difference, Working memory, Maze route finding

    Cite this