Policy transfer via modularity

8 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Sim-to-Real Transfer of Robotic Control with Dynamics Randomization (2017, background): “Clavera et al. demonstrated transferring pushing policies trained in simulation to a real PR2 [32].”
Learning Visual Affordances for Robotic Manipulation (2019, methodology): “Other methods [84, 48] explore the model-free planning of pushing motions to move objects to target positions that are more favorable for pre-designed grasping algorithms – the behaviors of which are typically handcrafted, fixed, and well-known in advance.”