Skip to content
Tagged articles

offline-to-online RL

2 articles · Page 1 of 1
Machine Heart
Machine Heart
Oct 29, 2026 · Artificial Intelligence

Value as Memory (VaM): Robots Achieve 95%+ Success in 4-Hour Continuous Tasks

VaM uses recent value predictions as task progress memory for robot policies, combined with a four-stage offline-to-online RL pipeline, enabling long-horizon deformable object manipulation and contact-rich assembly with 95%+ success over 4 hours, 29.4% improvement from value caching, and 32.8% higher sample efficiency from online RL.

VaMValue as Memorydeformable object manipulation
0 likes · 15 min read
Value as Memory (VaM): Robots Achieve 95%+ Success in 4-Hour Continuous Tasks
Machine Heart
Machine Heart
Apr 30, 2026 · Artificial Intelligence

How LWD Redefines Embodied AI Training with Fleet‑Scale Reinforcement Learning

LWD (Learning While Deploying) introduces a distributed multi‑robot reinforcement‑learning framework that continuously improves VLA policies during real‑world deployment, leveraging DIVL, QAM, dynamic n‑step TD and an asynchronous actor‑learner architecture to achieve over 90% success on five‑minute tasks and outperform traditional behavior‑cloning, HG‑Dagger and RECAP baselines.

Embodied AILWDRobotics
0 likes · 13 min read
How LWD Redefines Embodied AI Training with Fleet‑Scale Reinforcement Learning