Machine-Learning-6.867-homework icon indicating copy to clipboard operation
Machine-Learning-6.867-homework copied to clipboard

Published 20 hours ago • verified publisher icon peteflorence

SARSA

Open manuelli opened this issue 9 years ago • 1 comments

  • [x] Implement SARSA update
  • [x] Test it for convergence with a known policy, i.e. our simple controller
  • [x] Implement full SARSA policy updates

manuelli avatar Nov 19 '15 22:11 manuelli

Currently the discrete version of this is working. 4 inner and 4 outer bins seems to work reasonably well. Have implemented the continuous version with function approximation. Now need to test it our for convergence.

manuelli avatar Dec 01 '15 18:12 manuelli