Bayesian Meta-Learning for Few-Shot Policy Adaptation Across Robotic Platforms
Ali Ghadirzadeh,Xi Chen,Petra Poklukar,Chelsea Finn,Mårten Björkman,Danica Kragic,Ali Ghadirzadeh,Xi Chen,Petra Poklukar,Chelsea Finn,Mårten Björkman,Danica Kragic
Reinforcement learning methods can achieve significant performance but require a large amount of training data collected on the same robotic platform. A policy trained with expensive data is rendered useless after making even a minor change to the robot hardware. In this paper, we address the challenging problem of adapting a policy, trained to perform a task, to a novel robotic hardware platform ...
