A POMDP tree search technique estimates user reward weights from action discrepancies to reconcile and explain differences between algorithm and human decisions.
“Dave...I can assure you ...that it’s going to be all right
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2023 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Explanation through Reward Model Reconciliation using POMDP Tree Search
A POMDP tree search technique estimates user reward weights from action discrepancies to reconcile and explain differences between algorithm and human decisions.