Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revisionPrevious revision
Next revision
Previous revision
statnice:bakalar:b4b36zui [2026/05/29 14:42] – fix negascout knedl1kstatnice:bakalar:b4b36zui [2026/05/29 15:25] (current) – [Policy Improvement] knedl1k
Line 401: Line 401:
  
 $$ $$
-\pi'(s) = \arg\max_{a}\sum_{s'} P(s'|s,a),\bigl[R(s,a,s') + \gamma V^\pi(s')\bigr].+\pi'(s) = \arg\max_{a}\sum_{s'} P(s'|s,a)\bigl[R(s,a,s') + \gamma V^\pi(s')\bigr].
 $$ $$
  
Line 458: Line 458:
  
 $$ $$
-V_{k+1}(s) = \max_a \sum_{s'} P(s'|s,a),\bigl[R(s,a,s') + \gamma V_k(s')\bigr].+V_{k+1}(s) = \max_a \sum_{s'} P(s'|s,a)\left[R(s,a,s') + \gamma V_k(s')\right].
 $$ $$
  
Line 464: Line 464:
  
 $$ $$
-\pi^*(s) = \arg\max_a \sum_{s'} P(s'|s,a),\bigl[R(s,a,s') + \gamma V(s')\bigr].+\pi^*(s) = \arg\max_a \sum_{s'} P(s'|s,a)\bigl[R(s,a,s') + \gamma V(s')\bigr].
 $$ $$
  
Navigation

Playground

QR Code
QR Code statnice:bakalar:b4b36zui (generated for current page)