Title page for etd-0025116-130314


[Back to Results | New Search]

URN etd-0025116-130314
Author Chih-wen Lee
Author's Email Address No Public.
Statistics This thesis had been viewed 5345 times. Download 0 times.
Department Electrical Engineering
Year 2015
Semester 1
Degree Master
Type of Document
Language zh-TW.Big5 Chinese
Title Adaptive Exploration Strategies for Reinforcement Learning
Date of Defense 2016-01-23
Page Count 34
Keyword
  • Reinforce learning
  • Tabu search
  • State aggregation
  • trade-off between Exploration and Exploitation
  • decision tree
  • ε-greedy
  • Abstract Reinforcement learning through an agent to learn policy use trial and error method to achieve the goal, but when we want to apply it in a real environment, how to dividing state space becomes difficult to decide, another problem in reinforcement learning, agent takes an action in the learning process according to the policy, we will encounter how to balance exploitation and exploration, to explore a new areas in order to gain experience, or to get the maximum reward on existing knowledge. To solve problems, we proposed the decision tree-based adaptive state space segmentation algorithm and then use decreasing Tabu search and adaptive exploration strategies to solve the problem of exploitation and exploration on this method. Decreasing Tabu search will put the action into the Tabu list, after agent take an action. If the Tabu list is full, release the action, but the size of Tabu list will decreasing according to the number of successful reaching goals. Adaptive exploration strategy is based on information entropy, not tuning exploration rate by manually. Finally, a maze environment simulation is used to validate the proposed method, further to decrease the learning time.
    Advisory Committee
  • Ming-Yi Ju - chair
  • Yu-Jen Chen - co-chair
  • Kao-Shing Huang - advisor
  • Files
  • etd-0025116-130314.pdf
  • Indicate in-campus at 5 year and off-campus access at 5 year.
    Date of Submission 2016-01-25

    [Back to Results | New Search]


    Browse | Search All Available ETDs

    If you have more questions or technical problems, please contact eThesys