VLA Adaptation with Real and Simulated Data: A Case Study on Robotic Chess
Overview
This research examines the adaptation of Vision-language-action (VLA) models for a robotic chess task, specifically moving a king between named squares. The authors fine-tune the \pi_{0.5} model using varying amounts of teleoperated and simulated data. Key findings include that success rates in simulation scale with data volume, a learning-rate cool-down improves checkpoint comparison by up to 31 points, and pretraining on simulated data significantly aids performance when real data is limited. Conversely, experiments show that advanced methods like filtered behavior cloning and residual reinforcement learning did not yield measurable improvements over standard behavior cloning in this context. The paper releases the simulator, expert script, and real demonstration data.
Generated from attributed reports · Updated 5 hours ago
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
Control: teleoperated
“n. We study these questions on a task that requires both precise manipulation and spatial understanding of the scene. In this task, an SO-101 arm moves a chess king between two squares that are given only by their names, such as e4 and a5. We fine-tune $\pi_{0.5}$ with various dataset sizes and update budgets, using teleoperated demonstrations as well as simulated demonstrations from a randomized scripted expert that”
Exact source · revision 1Source owner not reported
Reported quantity · trials: 10 other · reported trials
“imitates the variability of human demonstrations. In simulation, the success rate scales with both data and updates. Importantly, we find that a short learning-rate cool-down adds up to 31 points and is necessary for comparing checkpoints, and that validation loss and action error are unreliable for model selection. On the real arm, we fine-tune on up to 256 teleoperated demonstrations and evaluate ten policies in 2”
Exact source · revision 1Source owner not reported
Reported quantity · points: 31 other · Basis not reported
“imitates the variability of human demonstrations. In simulation, the success rate scales with both data and updates. Importantly, we find that a short learning-rate cool-down adds up to 31 points and is necessary for comparing checkpoints, and that validation loss and action error are unreliable for model selection. On the real arm, we fine-tune on up to 256 teleoperated demonstrations and evaluate ten policies in 2”
Exact source · revision 1Source owner not reported
Reported quantity · demonstrations: 0.5 other · Basis not reported
“n. We study these questions on a task that requires both precise manipulation and spatial understanding of the scene. In this task, an SO-101 arm moves a chess king between two squares that are given only by their names, such as e4 and a5. We fine-tune $\pi_{0.5}$ with various dataset sizes and update budgets, using teleoperated demonstrations as well as simulated demonstrations from a randomized scripted expert that”
Exact source · revision 1Source owner not reported
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsSignalVLA Adaptation with Real and Simulated Data: A Case Study on Robotic Chess
This research examines the adaptation of Vision-language-action (VLA) models for a robotic chess task, specifically moving a king between named squares. The authors fine-tune the \pi_{0.5} model using varying amounts of teleoperated and simulated data. Key findings include that success rates in simulation scale with data volume, a learning-rate cool-down improves checkpoint comparison by up to 31 points, and pretraining on simulated data significantly aids performance when real data is limited. Conversely, experiments show that advanced methods like filtered behavior cloning and residual reinforcement learning did not yield measurable improvements over standard behavior cloning in this context. The paper releases the simulator, expert script, and real demonstration data.
Event coverage history
There is not enough continuous observation data to show a trend.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).