Fix zero-velocity local optimum in VBot navigation via reward reshaping and recovery threshold#5

Merged

Logic-TARS merged 8 commits intomainfrom

copilot/adjust-reward-function-weights

Feb 11, 2026

Commits on Feb 11, 2026

Initial plan
Copilot
committed
Implement zero-velocity trap fix: reward reshape, termination improvements, forced exploration

Copilot
and
Logic-TARS
committed
Add validation scripts and documentation for zero-velocity trap fix

Copilot
and
Logic-TARS
committed
Address code review: translate Chinese comments to English

Copilot
and
Logic-TARS
committed
Translate all Chinese comments to English for code consistency

Copilot
and
Logic-TARS
committed
Final translation: convert all remaining Chinese comments to English

Copilot
and
Logic-TARS
committed
Address code review: clarify comments and improve test logic documentation

Copilot
and
Logic-TARS
committed
Add implementation completion summary documentation

Copilot
and
Logic-TARS
committed