{"ID":2854674,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.14727","arxiv_id":"2510.14727","title":"The Pursuit of Diversity: Multi-Objective Testing of Deep Reinforcement Learning Agents","abstract":"Testing deep reinforcement learning (DRL) agents in safety-critical domains requires discovering diverse failure scenarios. Existing tools such as INDAGO rely on single-objective optimization focused solely on maximizing failure counts, but this does not ensure discovered scenarios are diverse or reveal distinct error types. We introduce INDAGO-Nexus, a multi-objective search approach that jointly optimizes for failure likelihood and test scenario diversity using multi-objective evolutionary algorithms with multiple diversity metrics and Pareto front selection strategies. We evaluated INDAGO-Nexus on three DRL agents: humanoid walker, self-driving car, and parking agent. On average, INDAGO-Nexus discovers up to 83% and 40% more unique failures (test effectiveness) than INDAGO in the SDC and Parking scenarios, respectively, while reducing time-to-failure by up to 67% across all agents.","short_abstract":"Testing deep reinforcement learning (DRL) agents in safety-critical domains requires discovering diverse failure scenarios. Existing tools such as INDAGO rely on single-objective optimization focused solely on maximizing failure counts, but this does not ensure discovered scenarios are diverse or reveal distinct error...","url_abs":"https://arxiv.org/abs/2510.14727","url_pdf":"https://arxiv.org/pdf/2510.14727v1","authors":"[\"Antony Bartlett\",\"Cynthia Liem\",\"Annibale Panichella\"]","published":"2025-10-16T14:25:55Z","proceeding":"cs.LG","tasks":"[\"cs.LG\"]","methods":"[\"Reinforcement Learning\"]","has_code":false}