method · first seen 21 Oct 2026
inverse temporal difference learning
Also: ITD
Recovering rewards from value functions by enforcing temporal-difference consistency in offline data.
Mentions per week
PapersCodeDiscussion
Earliest sources
- MA-UITD: Offline Multi-Agent Reward Inference for Characterizing Continuous Social BehaviorPapers · 21 Oct 2026 · Zeyuan Zhang, Yiyun Yang, Yuan Cheng, Herbert Zheng Wu, Yusi Chen
Latest sources
- MA-UITD: Offline Multi-Agent Reward Inference for Characterizing Continuous Social BehaviorPapers · 21 Oct 2026 · Zeyuan Zhang, Yiyun Yang, Yuan Cheng, Herbert Zheng Wu, Yusi Chen