RL framework for agile drone racing combines task-aware switching and physically informed procedural track generation to achieve 7.4x better zero-shot generalization to unseen tracks while maintaining competitive speeds.
Prioritized level replay
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
representative citing papers
The paper identifies four missing interfaces (data autolabelling, embodiment retargeting, physics-grounded world models, and video-based reward inference) as the central bottleneck beyond VLA scaling for robot intelligence.
Gated synthetic augmentations of a 10-task human base substitute for ~87 extra human RLVR tasks on aggregate held-out pass@1, with cost-adjusted trade rate ρ_cost in [1.4×, 11.6×].
A curriculum sampling questions with high variance in success rate improves reinforcement learning performance for LLM reasoning tasks.
citing papers explorer
-
Bridging Performance and Generalization in Reinforcement Learning for Agile Flight
RL framework for agile drone racing combines task-aware switching and physically informed procedural track generation to achieve 7.4x better zero-shot generalization to unseen tracks while maintaining competitive speeds.
-
Robots Need More than VLA and World Models
The paper identifies four missing interfaces (data autolabelling, embodiment retargeting, physics-grounded world models, and video-based reward inference) as the central bottleneck beyond VLA scaling for robot intelligence.
-
Trading Human Curation for Synthetic Augmentation in RLVR
Gated synthetic augmentations of a 10-task human base substitute for ~87 extra human RLVR tasks on aggregate held-out pass@1, with cost-adjusted trade rate ρ_cost in [1.4×, 11.6×].
-
Learning to Reason at the Frontier of Learnability
A curriculum sampling questions with high variance in success rate improves reinforcement learning performance for LLM reasoning tasks.