An Unified Approach to Inverse Reinforcement Learning by Oppositive Demonstrations
碩士 === 國立中山大學 === 電機工程學系研究所 === 104 === Reinforcement learning (RL) techniques use a reward function to correct a learning agent to solve sequential decision making problems through interactions with a dynamic environment, but it is hard to design the reward function in complex problems. Its design...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | en_US |
Published: |
2015
|
Online Access: | http://ndltd.ncl.edu.tw/handle/42949081673182197616 |