Too Much of a Good Thing: When sim2real Efforts Impede Policy Learning (And What to Do About It) - 2026-05-30 - Research Publication - While sim2real efforts are necessary for effective policy transfer to hardware, there is such a thing as too much of a good thing. We argue that sim2real efforts have led to misaligned incentives with policy learning… - source: arxiv.org
Virginia Tech thesis studies real-world reinforcement learning deployment on Apptronik Apollo - 2025-06-16 - Research Publication - The Virginia Tech master's thesis is titled Deploying Reinforcement Learning in the Real World: A Case Study on Apptronik Apollo. The repository record identifies the work as a humanoid-robotics and reinforcement-learning… - source: vtechworks.lib.vt.edu
Articles
Gemini Robotics 2 Brings Whole-Body Control to Apollo 2 - 2026-07-30 - Google DeepMind’s new VLA extends manipulation into walking and full-body humanoid control, while an on-device model targets faster adaptation across embodiments.
Apptronik raises $520M to scale Apollo humanoid production - 2026-02-11 - Apptronik’s Series A-X extension brings its total Series A to more than $935M, with new capital aimed at Apollo production, commercial deployments, and robot training facilities.