method · first seen 6 Oct 2026
hindsight goal relabeling
Also: hindsight relabeling, hindsight distillation, hindsight experience replay, hindsight-conditioned on-policy distillation
Reusing trajectories by relabeling them with goals that were actually reached, to learn goal-conditioned policies.
Mentions per week
PapersCodeDiscussion
Earliest sources
- Learning from Revision Consequences: Hindsight Meta-Experience Distillation for Self-Improving AgentsPapers · 6 Oct 2026 · Qianhan Feng, Zhongzhen Huang, Yakun Zhu, Xiaofan Zhang, Qi Dou
- An Informational Curse of Horizon in Goal-Conditioned Policy LearningPapers · 7 Oct 2026 · John L. Zhou, Yuxuan Dong, Jonathan C. Kao
- Failure Is the Mother of Success: Recovering Supervision with Grounding HindsightPapers · 14 Oct 2026 · Sheldon Yu, Tong Yu, Nikki Lijing Kuang, Zhendong Chu, Zhenwei Tang, Sungchul Ki…
- Distill Until Divergence: Error-Truncated Hindsight Distillation for Agentic RLPapers · 16 Oct 2026 · Yibin Huang, Conghui Zhu
- Learning Quality-Controllable Robot Policies with Iterative Hindsight RelabelingPapers · 27 Oct 2026 · Sinjae Kang, Dong Kyu Shin, Jaehong Kim, Kamin Lee, Hyoeun Kim, Kaixin Wang, Li…
Latest sources
- Learning Quality-Controllable Robot Policies with Iterative Hindsight RelabelingPapers · 27 Oct 2026 · Sinjae Kang, Dong Kyu Shin, Jaehong Kim, Kamin Lee, Hyoeun Kim, Kaixin Wang, Li…
- Distill Until Divergence: Error-Truncated Hindsight Distillation for Agentic RLPapers · 16 Oct 2026 · Yibin Huang, Conghui Zhu
- Failure Is the Mother of Success: Recovering Supervision with Grounding HindsightPapers · 14 Oct 2026 · Sheldon Yu, Tong Yu, Nikki Lijing Kuang, Zhendong Chu, Zhenwei Tang, Sungchul Ki…
- An Informational Curse of Horizon in Goal-Conditioned Policy LearningPapers · 7 Oct 2026 · John L. Zhou, Yuxuan Dong, Jonathan C. Kao
- Learning from Revision Consequences: Hindsight Meta-Experience Distillation for Self-Improving AgentsPapers · 6 Oct 2026 · Qianhan Feng, Zhongzhen Huang, Yakun Zhu, Xiaofan Zhang, Qi Dou