cs.LGNov 15, 2026

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

Authors: Ahmad Alfan Alfian Irfan, Nur Ahmad Khatim, Mansur Arief

Organizations: Information Technology, Universitas Muhammadiyah Yogyakarta, Yogyakarta, Indonesia. · Division of Information Science, Nara Institute of Science and Technology, Japan. · Department of Industrial and Systems Engineering, IRC Smart Mobility and Logistics, King Fahd University of Petroleum and Minerals (KFUPM), Saudi Arabia.

Abstract

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.

Figures & tables

Explore similar work

CardsList
  1. Learning from Mistakes: Rollout-Retrieval Lifelong Policy Learning for Autonomous Driving

    Jun 29, 2026Cheng Gong, Haoyang Wang, Chao Lu +2Autonomous Driving PlanningContinual RL

  2. DRIV-EX: Counterfactual Explanations for Driving LLMs

    Feb 28, 2026Amaia Cardiel, Eloi Zablocki, Elias Ramzi +1Counterfactual ExplanationsCounterfactual Reasoning in Language Models

  3. SAFER: Navigating the Exploration-Exploitation Dilemma in World-Model-Based Planning for Autonomous Driving

    Nov 15, 2026Yansong Qu, Zilin Huang, Zihao Sheng +2World Model-Based PlanningRL for Autonomous Driving