← 研踪 PaperTrailarXiv:2611.09139 · v1
CARGO: Causal Attribution and Responsibility-Guided Preventive Safe Multi-Agent Reinforcement Learning for Cooperative Driving
首次提交 2026-11-06 16:14
版本更新 2026-11-06 16:14
雷达观测 2026-11-09 11:19
摘要
This study presents Causal Attribution and Responsibility-Guided Optimization (CARGO), a multi-agent reinforcement learning framework for cooperative on-ramp merging in mixed traffic. A shared latent-context posterior and an action-conditioned response model estimate directed behavioral influence, with posterior uncertainty propagated into interaction-edge selection. Complementary attribution mechanisms couple signed influence with marginal team utility for cooperative reward shaping and assign responsibility from positive excess tail risk relative to a safe reference policy. Conditional diffusion generates future responses for action-dependent risk estimation. Responsibility-guided preventive optimization calibrates agent-specific risk-reduction requirements to local capacity within a policy trust region, using reserved safety margins, adaptive requirement scaling, and joint feasibility verification. Theoretical analysis establishes risk monotonicity and sufficient local conditions for non-decreasing environmental return under explicit assumptions. Experiments in highway-env across three traffic densities, together with controlled graph-recovery and attribution studies, support the effectiveness of the framework. Under high-density traffic, CARGO increases the success rate by 66.04\% and reduces the crash rate by 56.23\% relative to the best evaluated baseline for each metric.
作者备注：Abridged version containing the main results; the full version is under peer review and will be updated here upon acceptance
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 · 2026-11-06 16:14 · 最新观测版本
CARGO: Causal Attribution and Responsibility-Guided Preventive Safe Multi-Agent Reinforcement Learning for Cooperative Driving
This study presents Causal Attribution and Responsibility-Guided Optimization (CARGO), a multi-agent reinforcement learning framework for cooperative on-ramp merging in mixed traffic. A shared latent-context posterior and an action-conditioned response model estimate directed behavioral influence, with posterior uncertainty propagated into interaction-edge selection. Complementary attribution mechanisms couple signed influence with marginal team utility for cooperative reward shaping and assign responsibility from positive excess tail risk relative to a safe reference policy. Conditional diffusion generates future responses for action-dependent risk estimation. Responsibility-guided preventive optimization calibrates agent-specific risk-reduction requirements to local capacity within a policy trust region, using reserved safety margins, adaptive requirement scaling, and joint feasibility verification. Theoretical analysis establishes risk monotonicity and sufficient local conditions for non-decreasing environmental return under explicit assumptions. Experiments in highway-env across three traffic densities, together with controlled graph-recovery and attribution studies, support the effectiveness of the framework. Under high-density traffic, CARGO increases the success rate by 66.04\% and reduces the crash rate by 56.23\% relative to the best evaluated baseline for each metric.
查看此版本解读 →查看此版本原文 ↗