arXiv Computer Vision
DexPolicy: Scheduled Exploration for Trajectory-Guided Dexterous Manipulation
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv Machine Learning
Jun 11
OGPO: Sample Efficient Full-Finetuning of Generative Control Policies
arXiv:2605. 03065v2 Announce Type: replace Abstract: Generative control policies (GCPs), such as diffusion- and flow-based control policies, have emerged as effective parameterizations for robot learning.
arXiv AI
3d ago
DexHoldem: An Agentic Robotics Benchmark for Dexterous Manipulation in Texas Hold'em
arXiv:2605.18727v2 Announce Type: replace-cross Abstract: Evaluating embodied systems with real dexterous hardware requires more than isolated motor-skill tests: an agent must perceive a changing sce...
arXiv Computer Vision
Sep 21
DexPIE: Stable Dexterous Policy Improvement from Real-World Experience
DexPIE is a post‑training framework that improves dexterous manipulation policies using real‑world experience. It introduces a dexterous‑hand‑adapted intervention system and multi‑stage DAgger‑style data collection to enhance exploration, aligns training and inference to reduce distribution shift, and conditions the policy on a continuous optimality indicator for fine‑grained data quality use. In three real‑world tasks, DexPIE boosts success rates by 37.3% over a demonstration‑based baseline, outperforming all other methods and showing stronger robustness.
arXiv Computer Vision
Sep 15
Learning Manipulation-Sufficient Representations via Outcome Bottlenecks
arXiv:2609.13235v1 Announce Type: cross Abstract: Networked manipulation endpoints couple perception to actuation across compute- and bandwidth-limited links, yet commonly exchange dense geometric st...
arXiv AI
Sep 21
SynthDemo-RL: Breaking the Zero-Reward Barrier in VLA Adaptation with LLM-Guided Synthetic Demonstrations
SynthDemo‑RL introduces a teacher‑student framework that uses an automated teacher to generate successful manipulation trajectories from simulator‑privileged state, which are then distilled into a Vision‑Language‑Action (VLA) student via supervised fine‑tuning. The student is further refined with PPO using binary task‑success rewards. On the LIBERO‑PRO benchmark, SynthDemo‑RL rescues all 27 previously unsolvable tasks and achieves near‑perfect success rates, matching performance that would otherwise require human demonstrations.
arXiv Machine Learning
Sep 25
Uncertainty-Gated Exploration Noise Suppresses Task Collapse in Online RL Fine-Tuning of a Flow-Matching Vision-Language-Action Policy
The paper investigates task collapse—a failure mode where online RL fine‑tuning of a pretrained flow‑matching vision‑language‑action policy erodes performance on individual tasks—using a 450M‑parameter SmolVLA policy on LIBERO‑10. Three exploration‑noise strategies are compared: a fixed noise scale, a learned noise network, and an uncertainty‑gated controller that reallocates exploration based on novelty and competence signals without task labels. The uncertainty‑gated controller prevents task collapse across all tested seeds, whereas the other two approaches consistently cause collapse, demonstrating its effectiveness in preserving task performance during fine‑tuning.