跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.20019 · v1

D'BEAST: Logged Bad Experiences as Explanation for Autonomous Driving Agents

首次提交 2026-11-15 22:05
版本更新 2026-11-15 22:05
雷达观测 2026-11-17 12:06
arXiv ↗PDF ↗

摘要

Reinforcement learning agents learn from mistakes, yet their decisions can be difficult to trace back to those experiences. We investigate whether a tabular agent's decisions can be explained by its bad experiences, defined as the training transitions associated with safety or task events. A fixed training log is replayed from the same initial Q-table under three conditions. FULL retains all updates, SKIP omits bad-experience updates, and NEUTRALIZE retains those updates without their event penalties. We illustrate the method on six classic Markov decision processes and evaluate it in closed-loop driving in CARLA. On the full driving task, FULL reached the goal from 33 of 40 test starts, whereas SKIP and NEUTRALIZE reached it from none, indicating that the bad experiences carry decision-relevant information. At the local level, for 47 decisions shortly before a failure of SKIP or NEUTRALIZE, removing or neutralizing a small group of bad experiences, with a median size of one, caused the trained agent to select the failing policy's action in 46 cases. For this agent, the results indicate that its decisions can be explained by its bad experiences.

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

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 22:05 · 最新观测版本

D'BEAST: Logged Bad Experiences as Explanation for Autonomous Driving Agents

Reinforcement learning agents learn from mistakes, yet their decisions can be difficult to trace back to those experiences. We investigate whether a tabular agent's decisions can be explained by its bad experiences, defined as the training transitions associated with safety or task events. A fixed training log is replayed from the same initial Q-table under three conditions. FULL retains all updates, SKIP omits bad-experience updates, and NEUTRALIZE retains those updates without their event penalties. We illustrate the method on six classic Markov decision processes and evaluate it in closed-loop driving in CARLA. On the full driving task, FULL reached the goal from 33 of 40 test starts, whereas SKIP and NEUTRALIZE reached it from none, indicating that the bad experiences carry decision-relevant information. At the local level, for 47 decisions shortly before a failure of SKIP or NEUTRALIZE, removing or neutralizing a small group of bad experiences, with a median size of one, caused the trained agent to select the failing policy's action in 46 cases. For this agent, the results indicate that its decisions can be explained by its bad experiences.

查看此版本解读 →查看此版本原文 ↗