Sim-to-real transfer means training or pretraining a policy in a physics simulator and then running it on a real robot. Simulation offers abundant, safe, automatically labeled data. The cost is the reality gap: differences in rendering, contact dynamics, actuator response, timing and sensor noise between simulator and hardware.
Two 2017 papers define the standard toolkit. Tobin et al., "Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World", randomized rendering so that "the real world may appear to the model as just another variation". Peng et al., "Sim-to-Real Transfer of Robotic Control with Dynamics Randomization", randomized the simulator's dynamics during training so that policies adapt to dynamics they were not trained on.
For the imitation-learning policies in this matrix the pattern is usually different. Models are trained on real teleoperated data and evaluated in simulated benchmarks such as LIBERO and Meta-World, which LeRobot provides as environments. A high LIBERO success rate for OpenVLA-OFT or SmolVLA is a simulation result; it says nothing directly about an SO-101 on a desk. Compatibility cells therefore keep inference_sim and inference_real as separate capabilities.
A common misconception is that a policy which works in simulation will transfer once the images look realistic. Appearance is only one part of the gap. Unmodeled dynamics, actuator delay and a mismatched control rate break transfer just as reliably, which is why Peng et al. randomized dynamics rather than visuals. The embodiment gap is a separate problem: it concerns differences between robots, not between a robot and its simulation.