Skip to main content

# Adaptive Rollout

2 related articles

Subscribe to updates

arXiv Sep 29, 2026
FastRL brings about 2.07x training speedup and roughly 1.64% average accuracy gain to GRPO-style methods via advantage-aware pruning and adaptive sampling
The work proposes FastRL, a plug-and-play reinforcement learning framework that selectively preserves high-advantage trajectories while maximizing inter-trajectory gradient diversity through an advantage-aware pruning strategy, and dynamically adjusts sampling scale across training stages based on historical pruning distributions via an adaptive rollout sampling mechanism, achieving an average 2.07x training speedup on Geometry3K and GeoQA8K-R1V along with approximately 1.64% improvement in average accuracy on visual reasoning benchmarks, and integrating seamlessly into GRPO, DAPO, and GSPO variants.
The work proposes FastRL, a plug-and-play reinforcement learning framework that selectively preserves high-advantage trajectories while maximizing inter-trajectory gradient diversity through an advantage-aware pruning strategy, and dynamically adjusts sampling scale across training stages based on historical pruning distributions via an adaptive rollout sampling mechanism, achieving an average 2.07x training speedup on Geometry3K and GeoQA8K-R1V along with approximately 1.64% improvement in average accuracy on visual reasoning benchmarks, and integrating seamlessly into GRPO, DAPO, and GSPO variants.
Jinan University Guangdong University of Education
Jiahua Yang（First author）
FastRL advantage-aware pruning Adaptive Rollout GRPO Visual Reasoning
arXiv Sep 29, 2026
DroneWAM cuts drone visual-navigation inference to 483 ms with JEPA latent prediction and adaptive rollout, lifting closed-loop progress from 0.510 to 0.774
The work presents DroneWAM, an efficient world-action model for drone visual navigation that uses a JEPA-based architecture to predict future states directly in representation space, a pretrained Resampler to compress dense encoder features into fewer latent tokens, and a preference-trained Gate that adaptively allocates prediction depth per scene, alongside DroneNav-6D, a simulated dataset with synchronized RGB observations, 6-DoF flight trajectories, control commands, and randomized wind disturbances; on DroneNav-6D it achieves the best trajectory accuracy among the compared methods, and adaptive rollout reduces the average prediction depth from 8 to 4.58 while improving trajectory accuracy.
The work presents DroneWAM, an efficient world-action model for drone visual navigation that uses a JEPA-based architecture to predict future states directly in representation space, a pretrained Resampler to compress dense encoder features into fewer latent tokens, and a preference-trained Gate that adaptively allocates prediction depth per scene, alongside DroneNav-6D, a simulated dataset with synchronized RGB observations, 6-DoF flight trajectories, control commands, and randomized wind disturbances; on DroneNav-6D it achieves the best trajectory accuracy among the compared methods, and adaptive rollout reduces the average prediction depth from 8 to 4.58 while improving trajectory accuracy.
Nanjing University Hohai University Shanghai Jiao Tong University East China Normal University Southeast University Ministry of Water Resources of the People's Republic of China
Liang Yao（First author）
DroneWAM DroneNav-6D Adaptive Rollout Joint-Embedding Predictive Architecture Drone Visual Navigation

You’re all caught up