作者位次 #7/13ICML 2026Poster· Reinforcement Learning / Batch/Offline
When Does Predictive Inverse Dynamics Outperform Behavior Cloning?
Lukas Schäfer · Pallavi Choudhury · Abdelhak Lemkhenter · Chris Lovett · Somjit Nath · Luis França · Matheus Mendonca · Alex Lamb · Riashat Islam · Siddhartha Sen · John Langford · Katja Hofmann · Sergio Valcarcel Macua
强化学习与后训练OpenReview