{"ID":2884426,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.07029","arxiv_id":"2508.07029","title":"From Imitation to Optimization: A Comparative Study of Offline Learning for Autonomous Driving","abstract":"Learning robust driving policies from large-scale, real-world datasets is a central challenge in autonomous driving, as online data collection is often unsafe and impractical. While Behavioral Cloning (BC) offers a straightforward approach to imitation learning, policies trained with BC are notoriously brittle and suffer from compounding errors in closed-loop execution. This work presents a comprehensive pipeline and a comparative study to address this limitation. We first develop a series of increasingly sophisticated BC baselines, culminating in a Transformer-based model that operates on a structured, entity-centric state representation. While this model achieves low imitation loss, we show that it still fails in long-horizon simulations. We then demonstrate that by applying a state-of-the-art Offline Reinforcement Learning algorithm, Conservative Q-Learning (CQL), to the same data and architecture, we can learn a significantly more robust policy. Using a carefully engineered reward function, the CQL agent learns a conservative value function that enables it to recover from minor errors and avoid out-of-distribution states. In a large-scale evaluation on 1,000 unseen scenarios from the Waymo Open Motion Dataset, our final CQL agent achieves a 3.2x higher success rate and a 7.4x lower collision rate than the strongest BC baseline, proving that an offline RL approach is critical for learning robust, long-horizon driving policies from static expert data.","short_abstract":"Learning robust driving policies from large-scale, real-world datasets is a central challenge in autonomous driving, as online data collection is often unsafe and impractical. While Behavioral Cloning (BC) offers a straightforward approach to imitation learning, policies trained with BC are notoriously brittle and suff...","url_abs":"https://arxiv.org/abs/2508.07029","url_pdf":"https://arxiv.org/pdf/2508.07029v2","authors":"[\"Antonio Guillen-Perez\"]","published":"2025-08-09T16:03:10Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\",\"cs.RO\",\"eess.SY\"]","methods":"[\"Reinforcement Learning\",\"Transformer\"]","has_code":false}