What Matters for Latent Actions in Robot Learning
- Published
- Source
- arXiv
- Paper number
- 964
- Field
- Robotics
- arXiv ID
- 2608.19613
Key points
- It compared 41 latent action model (LAM) design choices under unified conditions across 3 simulation benchmarks + a real Franka robot.
- A latent-action dimension of 32 was optimal for both single-arm and dual-arm robots, and additional regularization was unnecessary when pretraining regularization was done properly.
- Fine-tuning the VLM backbone with latent actions beforehand raised success on 4 real-robot tasks from 64.75%→79.25% (+14.5 percentage points).
- The LAM-tuned model reached 85% success after just 10k steps, surpassing the baseline's performance at 40k steps (76.25%) and demonstrating data efficiency.
- The simple reconstruction (FDM) metric was a more reliable predictor of latent-action quality than the conventionally used MLP-probe metric.
Paper links
External research summaries. These are not HDATF publications or measured product results.