デモンストレーションからの適応的カリキュラム生成による視覚運動制御のsim-to-real転移
Adaptive Curriculum Generation from Demonstrations for Sim-to-Real Visuomotor Control
デモ軌跡のサンプリング位置とシミュレーション設定を適応的に制御してタスク難易度を段階的に上げ、視覚ベースの強化学習方策を実世界へゼロショット転移させる手法を提案した。
著者: Lukas Hermann, Max Argus, Andreas Eitel, Artemij Amiranashvili, Wolfram Burgard, Thomas Brox
分類: cs.RO, cs.CV, cs.LG
原文アブストラクト
We propose Adaptive Curriculum Generation from Demonstrations (ACGD) for reinforcement learning in the presence of sparse rewards. Rather than designing shaped reward functions, ACGD adaptively sets the appropriate task difficulty for the learner by controlling where to sample from the demonstration trajectories and which set of simulation parameters to use. We show that training vision-based control policies in simulation while gradually increasing the difficulty of the task via ACGD improves the policy transfer to the real world. The degree of domain randomization is also gradually increased through the task difficulty. We demonstrate zero-shot transfer for two real-world manipulation tasks: pick-and-stow and block stacking. A video showing the results can be found at https://lmb.informatik.uni-freiburg.de/projects/curriculum/
