← 研踪 PaperTrailarXiv:2611.19969 · v1
Value and Policy Calibration from Execution Feedback for Socially Compatible Driving
首次提交 2026-11-15 20:23
版本更新 2026-11-15 20:23
雷达观测 2026-11-17 12:06
摘要
Autonomous vehicle (AV) decisions at intersections affect the delay, braking, and motion smoothness of surrounding human-driven vehicles (HDVs). Learning socially compatible behavior requires connecting imagined interaction outcomes with feedback from executed actions. We propose a world-model reinforcement learning framework combines imagined policy improvement with direct value and policy calibration from finalized interactions, balancing AV progress with HDV interaction burden. An interaction-aware latent model supports imagination, while off-policy correction and replay updates enable observed rewards and transitions to supervise both the critic and actor. Simulation experiments at an unsignalized intersection achieve a 100% success and reductions in following-HDV acceleration variation of 65.5% and 44.0% relative to PIWM and DreamerV3, respectively. Ablations identify complementary roles for value calibration in reducing HDV burden and policy calibration in improving passage efficiency. Tests under out-of-distribution traffic shifts further show lower ego jerk and HDV acceleration variation than PIWM at comparable passage times.
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v1 · 2026-11-15 20:23 · 最新观测版本
Value and Policy Calibration from Execution Feedback for Socially Compatible Driving
Autonomous vehicle (AV) decisions at intersections affect the delay, braking, and motion smoothness of surrounding human-driven vehicles (HDVs). Learning socially compatible behavior requires connecting imagined interaction outcomes with feedback from executed actions. We propose a world-model reinforcement learning framework combines imagined policy improvement with direct value and policy calibration from finalized interactions, balancing AV progress with HDV interaction burden. An interaction-aware latent model supports imagination, while off-policy correction and replay updates enable observed rewards and transitions to supervise both the critic and actor. Simulation experiments at an unsignalized intersection achieve a 100% success and reductions in following-HDV acceleration variation of 65.5% and 44.0% relative to PIWM and DreamerV3, respectively. Ablations identify complementary roles for value calibration in reducing HDV burden and policy calibration in improving passage efficiency. Tests under out-of-distribution traffic shifts further show lower ego jerk and HDV acceleration variation than PIWM at comparable passage times.
查看此版本解读 →查看此版本原文 ↗