Embodied AI TopConf · ICLR2026

Policy Likelihood-based Query Sampling and Critic-Exploited Reset for Efficient Preference-based Reinforcement Learning

ICLR2026 / Policy

策略学习触觉加速/部署
新标签打开 PDF新标签打开 Paper
Policy Likelihood-based Query Sampling and Critic-Exploited Reset for Efficient Preference-based Reinforcement Learning figure
在线论文 PDF（可滚动查看）

精读笔记

精读笔记尚未生成。