Football Table RL: Difference between revisions
Jump to navigation
Jump to search
(Created page with '==Reinforcement Learning== The football table employs on-line value iteration, namely <code>Greedy-GQ<math>(\lambda)</math></code> and <code>Approximate-Q<math>(\lambda)</math><…') |
No edit summary |
||
| Line 1: | Line 1: | ||
==Reinforcement Learning== | ==Reinforcement Learning== | ||
The football table employs on-line value iteration, namely | The football table employs on-line value iteration, namely Greedy-GQ<math>(\lambda)</math> and Approximate-Q<math>(\lambda)</math>. | ||
==Value Function Approximation | ==Value Function Approximation== | ||
Revision as of 15:21, 11 September 2013
Reinforcement Learning
The football table employs on-line value iteration, namely Greedy-GQ[math]\displaystyle{ (\lambda) }[/math] and Approximate-Q[math]\displaystyle{ (\lambda) }[/math].