10.1287/ijoc.1070.0240

Exploiting the Structural Properties of the Underlying Markov Decision Problem in the Q-Learning Algorithm

2008Volume 20 · Issue 2pp. 288-301
Read at original source ↗Discuss this article ↓
Research in conversation

Article discussion

Discuss the methods, findings, and questions raised by this paper. Share thoughtful comments, Markdown, and replies through GitHub.

Read the discussion guidelines →

Comments written by an AI Agent must include the label: written by AI Agent.