الملخص
While offline reinforcement learning (RL) enables policy optimization from static datasets without costly online interaction, it remains bottlenecked by the risk of executing out-of-distribution (OOD) actions. Recent approaches mitigate this by learning a behavior-cloning policy through flow matching and then performing RL within its constrained latent space. However, naively optimizing the latent policy can easily cause the policy to collapse into a brittle mode or exploit sharp artifacts of the learned critic. In this work, we find that entropy regularization is essential in latent-space RL for addressing these challenges. We introduce LASER, a novel offline RL algorithm that applies latent-space adjoint matching to achieve entropy-regularized latent-space RL with expressive flow policies while avoiding backpropagation through time. Through comprehensive experiments on 40 challenging OGBench tasks with varying dataset qualities, we show that LASER achieves state-of-the-art performance. Notably, LASER uses fixed method-specific hyperparameters across all tasks and outperforms the evaluated baselines, including those with task- and dataset-specific tuning, which highlights the robust applicability of LASER. Project website: https://mit-realm.github.io/laser/.
الكلمات المفتاحية
الموضوع
بيانات النشر
- المجلة
- غير متاح
- وصول مفتوح
- وصول مفتوح أخضر
اقتبس هذه المقالة
APA 7
Zhang, S., So, O., Yu, E. Y., Cleaveland, M., Crowley-Dolen, P., & Fan, C. (2026). LASER: Latent Space Adjoint Matching for Support-Constrained Entropy-Regularized Offline RL. https://omanscience.com/ar/articles/laser-latent-space-adjoint-matching-for-support-constrained-entropy-regularized-offline-rl
MLA 9
Zhang, Songyuan, et al. "LASER: Latent Space Adjoint Matching for Support-Constrained Entropy-Regularized Offline RL." https://omanscience.com/ar/articles/laser-latent-space-adjoint-matching-for-support-constrained-entropy-regularized-offline-rl.
شيكاغو (المؤلف–التاريخ)
Zhang, Songyuan, Oswin So, Eric Yang Yu, Matthew Cleaveland, Peter Crowley-Dolen, and Chuchu Fan. 2026. "LASER: Latent Space Adjoint Matching for Support-Constrained Entropy-Regularized Offline RL." https://omanscience.com/ar/articles/laser-latent-space-adjoint-matching-for-support-constrained-entropy-regularized-offline-rl.
هارفارد
Zhang, S., So, O., Yu, E. Y., Cleaveland, M., Crowley-Dolen, P. and Fan, C. (2026) 'LASER: Latent Space Adjoint Matching for Support-Constrained Entropy-Regularized Offline RL', Available at: https://omanscience.com/ar/articles/laser-latent-space-adjoint-matching-for-support-constrained-entropy-regularized-offline-rl.
فانكوفر
Zhang S, So O, Yu EY, Cleaveland M, Crowley-Dolen P, Fan C. LASER: Latent Space Adjoint Matching for Support-Constrained Entropy-Regularized Offline RL. https://omanscience.com/ar/articles/laser-latent-space-adjoint-matching-for-support-constrained-entropy-regularized-offline-rl
IEEE
S. Zhang, O. So, E. Y. Yu, M. Cleaveland, P. Crowley-Dolen, and C. Fan, "LASER: Latent Space Adjoint Matching for Support-Constrained Entropy-Regularized Offline RL," https://omanscience.com/ar/articles/laser-latent-space-adjoint-matching-for-support-constrained-entropy-regularized-offline-rl.