継続的ロボット学習における創発的な「自己」の証拠
Evidence of an Emergent "Self" in Continual Robot Learning
ロボットに継続学習(可変タスク)を行わせると、不変なサブネットワークが形成され、これが「自己」に相当する可能性を示した。このサブネットワークは適応に重要で、損傷すると性能が低下する。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Adidev Jhunjhunwala, Judah Goldfeder, Hod Lipson
分類: cs.RO, cs.AI, cs.LG
原文アブストラクト
A key challenge to understanding self-awareness has been a principled way of quantifying whether an intelligent system has a concept of a "self", and if so how to differentiate the "self" from other cognitive structures. We propose that the "self" can be isolated by seeking the invariant portion of cognitive process that changes relatively little compared to more rapidly acquired cognitive skills - because our self is the most persistent aspect of our experiences. We used this principle to analyze the cognitive structure of robots under two conditions: One robot learns a constant task, while a second undergoes continual learning under variable tasks. We find that robots subjected to continual learning develop an invariant subnetwork that is significantly more stable (p < 0.001) compared to the control, and that this subnetwork is also functionally important: preserving it aids adaptation while damaging it impairs performance. We validate this pattern across three different robots spanning locomotion and manipulation.
