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

Jun 29, 2026

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

Autonomous driving policies should be able to improve continually as deployment exposes them to increasingly diverse and long-tail traffic situations. However, most learning-based policies are trained or fine-tuned on expert demonstrations and then rely largely on generalization to handle challenging closed-loop scenarios, lacking an explicit mechanism to correct and retain the mistakes exposed in these scenarios. This paper studies autonomous driving policy improvement from a lifelong learning perspective: Can a pretrained policy improve continually by accumulating corrective knowledge derived from its own mistakes, while retaining previously acquired driving competence? To answer this question, we propose Rollout-Retrieval Lifelong Policy Learning (R2^2LPL), a policy learning framework that retrieves corrective targets from recoverable policy-induced mistakes and retains the resulting knowledge through lifelong policy learning. R^2LPL addresses a key bottleneck in continual policy improvement: closed-loop mistakes reveal where the policy is weak, but do not directly specify what the policy should learn. By filtering recoverable mistake-related states and retrieving feasible corrective targets, R2^2LPL turns sparse failure evidence into compact supervised knowledge for stable and sample-efficient policy improvement. We evaluate R2^2LPL on large-scale closed-loop nuPlan benchmarks. With only a few rollout and continual-learning cycles, R2^2LPL elevates a learning-based planner with moderate initial performance to state-of-the-art performance across the evaluated benchmarks, especially on the challenging and long-tail Test14-hard split. These results demonstrate the effectiveness of R2^2LPL in converting recoverable closed-loop mistakes into corrective knowledge for sustained policy improvement.
Feb 28, 2026

DRIV-EX: Counterfactual Explanations for Driving LLMs

Large language models (LLMs) are increasingly used as reasoning engines in autonomous driving, yet their decision-making remains opaque. We propose to study their decision process through counterfactual explanations, which identify the minimal semantic changes to a scene description required to alter a driving plan. We introduce DRIV-EX, a method that leverages gradient-based optimization on continuous embeddings to identify the input shifts required to flip the model's decision. Crucially, to avoid the incoherent text typical of unconstrained continuous optimization, DRIV-EX uses these optimized embeddings solely as a semantic guide: they are used to bias a controlled decoding process that re-generates the original scene description. This approach effectively steers the generation toward the counterfactual target while guaranteeing the linguistic fluency, domain validity, and proximity to the original input, essential for interpretability. Evaluated using the LC-LLM planner on a textual transcription of the highD dataset, DRIV-EX generates valid, fluent counterfactuals more reliably than existing baselines. It successfully exposes latent biases and provides concrete insights to improve the robustness of LLM-based driving agents. The code is available at "https://github.com/Amaia-CARDIEL/DRIV_EX" .
Nov 15, 2026

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

An autonomous vehicle must foresee the consequences of its actions, especially in the rare, time-critical situations where crashes happen. A world model offers this foresight, but only within the coverage of its training data, which poses an exploration-exploitation dilemma. Within this coverage a planner can hardly improve on the data, and beyond it the model's errors mislead it. Logs of competent driving rarely contain the failures that would widen the coverage, and agents that learn from interaction gain them only by failing themselves, without being shown what to do instead. We propose SAFER, a framework that learns offline from failures that others make, judged by an expert, and keeps learning online from its own driving. Offline, partially trained agents and scripted, recoverable perturbations Stage failures in simulation, and an expert Annotates every visited state with its action and value, so that much of what the planner explores is covered before it drives. In planning, a chunked latent world model Foresees the consequences fast enough for real-time use, and a risk-aware sampling-based planner Evaluates candidate maneuvers by their return minus a bounded collision penalty. Online, a loop continuously Refines the model wherever this driving leaves the coverage of the offline data. In closed-loop evaluation against the compared methods, SAFER reaches the highest route completion and reward per step on the CARLA Leaderboard routes, 0.95 and 0.77 from a privileged bird's-eye view, and the highest episode reward in MetaDrive, 53.4 in regular and 49.0 in safety-critical traffic. Project page: https://ys-qu.github.io/safer-website.