{"slug": "disagreement-regularized-imitation-learning-for-image-based-continuous-control", "title": "Disagreement-Regularized Imitation Learning for Image-Based Continuous Control with Gaussian and Beta Policies", "summary": "A controlled CarRacing study found that Disagreement-Regularized Imitation Learning (DRIL), which converts disagreement among cloned policies into a reinforcement-learning reward, improved over the strongest behavior-cloning mean by 61% with clipped-action demonstrations and by 112% with bounded-action demonstrations in the few-demonstration setting. The arXiv paper reports that with 20 trajectories the DRIL advantage narrowed, and in the bounded-action regime Beta behavior cloning remained about 7% above the best DRIL checkpoint. Each retained policy was evaluated over 100 procedurally generated episodes using a five-policy Gaussian disagreement ensemble.", "body_md": "arXiv:2609.38407v1 Announce Type: new \nAbstract: Purpose: Behavior cloning can accumulate errors when a learned controller visits states outside the demonstrated distribution. This study evaluates whether Disagreement-Regularized Imitation Learning (DRIL), which converts disagreement among cloned policies into a reinforcement-learning reward, improves image-based continuous control. Methods: A controlled CarRacing study combines Gaussian and Beta learner policies, demonstrations from either a clipped Gaussian expert or an intrinsically bounded Beta expert, one or 20 trajectories, deterministic and stochastic evaluation, and three retained stages: behavior cloning, the highest 10-episode training-score checkpoint, and the final DRIL checkpoint. The disagreement ensemble contains five Gaussian policies in every variant. Each retained policy is evaluated over 100 procedurally generated episodes. Results: Score-selected DRIL produced its largest gains in the few-demonstration setting, improving over the strongest behavior-cloning mean by 61% with clipped-action demonstrations and by 112% with bounded-action demonstrations. With 20 trajectories, the advantage of DRIL narrowed; in the bounded-action regime, Beta behavior cloning remained about 7% above the best DRIL checkpoint. The experiments also show that the informativeness of the disagreement reward changes with the learner representation and training stage. Conclusion: DRIL can substantially improve few-demonstration visual continuous control, while bounded Beta policies provide strong behavior-cloning performance when more demonstrations are available. The results highlight the joint importance of learner support,ensemble response, and checkpoint selection.", "url": "https://wpnews.pro/news/disagreement-regularized-imitation-learning-for-image-based-continuous-control", "canonical_source": "https://arxiv.org/abs/2609.38407", "published_at": "2026-10-02 04:00:00+00:00", "updated_at": "2026-10-02 04:16:41.142041+00:00", "lang": "en", "topics": ["machine-learning", "robotics", "ai-research", "autonomous-vehicles"], "entities": ["DRIL", "CarRacing", "arXiv"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/disagreement-regularized-imitation-learning-for-image-based-continuous-control", "markdown": "https://wpnews.pro/news/disagreement-regularized-imitation-learning-for-image-based-continuous-control.md", "text": "https://wpnews.pro/news/disagreement-regularized-imitation-learning-for-image-based-continuous-control.txt", "jsonld": "https://wpnews.pro/news/disagreement-regularized-imitation-learning-for-image-based-continuous-control.jsonld"}}