信念接地ネットワーク:部分観測下でのロボット学習を加速する手法
Belief-Grounded Networks for Accelerated Robot Learning under Partial Observability
部分観測環境で履歴を簡潔に要約する補助損失を用いて方策を学習するBGNを提案し、触覚センシングを含むベンチマークで既存手法を上回り実機転移も成功した。
著者: Hai Nguyen, Brett Daley, Xinchao Song, Christopher Amato, Robert Platt
分類: cs.RO, cs.AI, cs.LG
原文アブストラクト
Many important robotics problems are partially observable in the sense that a single visual or force-feedback measurement is insufficient to reconstruct the state. Standard approaches involve learning a policy over beliefs or observation-action histories. However, both of these have drawbacks; it is expensive to track the belief online, and it is hard to learn policies directly over histories. We propose a method for policy learning under partial observability called the Belief-Grounded Network (BGN) in which an auxiliary belief-reconstruction loss incentivizes a neural network to concisely summarize its input history. Since the resulting policy is a function of the history rather than the belief, it can be executed easily at runtime. We compare BGN against several baselines on classic benchmark tasks as well as three novel robotic touch-sensing tasks. BGN outperforms all other tested methods and its learned policies work well when transferred onto a physical robot.
