← Back to Benchmarks
simmediumsim-to-realmetric · varies

Beyond Imitation: Reinforcement Learning-Based Sim-Real Co-Training for VLA Models

Description

Simulation offers a scalable and low-cost way to enrich vision-language-action (VLA) training, reducing reliance on expensive real-robot demonstrations. However, most sim-real co-training methods rely on supervised fine-tuning (SFT), which treats simulation as a static source of demonstrations and does not exploit large-scale closed-loop interaction. Consequently, real-world gains and generalization are often limited. In this paper, we propose an \underline{\textit{RL}}-based sim-real \underline

Source

http://arxiv.org/abs/2602.12628v3