行動の自己組織化による継続的ロボット学習のためのタスク推論
Behavior Self-Organization Supports Task Inference for Continual Robot Learning
示範行動を逐次的に自己組織化して行動埋め込みを教師なし学習し、最近傍探索でタスクを推論する継続学習手法を提案。タスク分布の仮定や探索を必要とせず、汎化性能と収束速度で既存手法を上回る。
著者: Muhammad Burhan Hafez, Stefan Wermter
分類: cs.RO, cs.AI, cs.LG
原文アブストラクト
Recent advances in robot learning have enabled robots to become increasingly better at mastering a predefined set of tasks. On the other hand, as humans, we have the ability to learn a growing set of tasks over our lifetime. Continual robot learning is an emerging research direction with the goal of endowing robots with this ability. In order to learn new tasks over time, the robot first needs to infer the task at hand. Task inference, however, has received little attention in the multi-task learning literature. In this paper, we propose a novel approach to continual learning of robotic control tasks. Our approach performs unsupervised learning of behavior embeddings by incrementally self-organizing demonstrated behaviors. Task inference is made by finding the nearest behavior embedding to a demonstrated behavior, which is used together with the environment state as input to a multi-task policy trained with reinforcement learning to optimize performance over tasks. Unlike previous approaches, our approach makes no assumptions about task distribution and requires no task exploration to infer tasks. We evaluate our approach in experiments with concurrently and sequentially presented tasks and show that it outperforms other multi-task learning approaches in terms of generalization performance and convergence speed, particularly in the continual learning setting.
