強化学習による深層予測ポリシーの訓練
Deep Predictive Policy Training using Reinforcement Learning
画像から一連のモーター指令を予測する深層ポリシーを、知覚・ポリシー・行動の3層構造で構成し、約180回の実機試行だけでPR2ロボットの物体把持とボール投げを学習させた。
著者: Ali Ghadirzadeh, Atsuto Maki, Danica Kragic, Mårten Björkman
分類: cs.RO
原文アブストラクト
Skilled robot task learning is best implemented by predictive action policies due to the inherent latency of sensorimotor processes. However, training such predictive policies is challenging as it involves finding a trajectory of motor activations for the full duration of the action. We propose a data-efficient deep predictive policy training (DPPT) framework with a deep neural network policy architecture which maps an image observation to a sequence of motor activations. The architecture consists of three sub-networks referred to as the perception, policy and behavior super-layers. The perception and behavior super-layers force an abstraction of visual and motor data trained with synthetic and simulated training samples, respectively. The policy super-layer is a small sub-network with fewer parameters that maps data in-between the abstracted manifolds. It is trained for each task using methods for policy search reinforcement learning. We demonstrate the suitability of the proposed architecture and learning framework by training predictive policies for skilled object grasping and ball throwing on a PR2 robot. The effectiveness of the method is illustrated by the fact that these tasks are trained using only about 180 real robot attempts with qualitative terminal rewards.
