A POMDP tree search technique estimates user reward weights from action discrepancies to reconcile and explain differences between algorithm and human decisions.
Explanation-Based Reward Coaching to Improve Human Performance via Reinforcement Learning,
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.