Skip to content

Fixed issue in VI with SOR - #12

Merged
areenberg merged 1 commit into
masterfrom
sor_calculation
Oct 9, 2026
Merged

areenberg merged 1 commit into
masterfrom
sor_calculation

Conversation

@areenberg

@areenberg areenberg commented Oct 9, 2026 •

Copy link
Copy Markdown
Owner

Fixed an issue in method valueIterationSORGenMDP which led to a wrong value calculation and correspondingly wrong policy.

@areenberg areenberg linked an issue Oct 9, 2026 that may be closed by this pull request
@areenberg
areenberg merged commit f755b37 into master Oct 9, 2026
5 checks passed
areenberg added a commit that referenced this pull request Oct 9, 2026
Patch bump: fixes incorrect VI+SOR values/policy on general MDP models
(ModifiedPolicyIteration::valueIterationSORGenMDP used the policy's
stored action for the reward term instead of the candidate action
being evaluated - issue #11). No API changes. Verified via PR #12's
full build+test matrix across Linux, Windows, and macOS.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

Incorrect values and policy with VI + SOR on a minimal discounted MDP

1 participant