Skip to content

Latest commit

 

History

History
16 lines (9 loc) · 438 Bytes

incremental-learning-1.md

File metadata and controls

16 lines (9 loc) · 438 Bytes

Incremental Learning

Q-LEARN

Q-Learning

  • Markov chain problem, (state, action, new state, reward)
  • Lots of Exploration in the beginning, then exploitation
  • Returns optimal policy.
  • Refer to youtube here

RL IN DL

A review paper about RL in DL