ノイズ環境下での不確実性を考慮した数ショットモデル適応
Few-shot model-based adaptation in noisy conditions
カルマンフィルタに基づく不確実性考慮型ニューラルネットワークで、ノイズのある実環境におけるダイナミクスモデルの数ショット適応を実現し、LSTMベースや強化学習ベースの手法より適応誤差を低減した。
著者: Karol Arndt, Ali Ghadirzadeh, Murtaza Hazara, Ville Kyrki
分類: cs.LG, cs.RO
原文アブストラクト
Few-shot adaptation is a challenging problem in the context of simulation-to-real transfer in robotics, requiring safe and informative data collection. In physical systems, additional challenge may be posed by domain noise, which is present in virtually all real-world applications. In this paper, we propose to perform few-shot adaptation of dynamics models in noisy conditions using an uncertainty-aware Kalman filter-based neural network architecture. We show that the proposed method, which explicitly addresses domain noise, improves few-shot adaptation error over a blackbox adaptation LSTM baseline, and over a model-free on-policy reinforcement learning approach, which tries to learn an adaptable and informative policy at the same time. The proposed method also allows for system analysis by analyzing hidden states of the model during and after adaptation.
