オンラインガウス過程状態空間モデル:部分観測力学系の学習と計画
Online Gaussian Process State-Space Model: Learning and Planning for Partially Observable Dynamical Systems
逐次到着する時系列データからガウス過程状態空間モデルを破滅的忘却なくオンライン学習する手法を提案し、ベイズフィルタと軌道最適化を組み合わせて部分観測系の強化学習に応用した。
著者: Soon-Seo Park, Young-Jin Park, Youngjae Min, Han-Lim Choi
分類: cs.RO
原文アブストラクト
This paper proposes an online learning method of Gaussian process state-space model (GP-SSM). GP-SSM is a probabilistic representation learning scheme that represents unknown state transition and/or measurement models as Gaussian processes (GPs). While the majority of prior literature on learning of GP-SSM are focused on processing a given set of time series data, data may arrive and accumulate sequentially over time in most dynamical systems. Storing all such sequential data and updating the model over entire data incur large amount of computational resources in space and time. To overcome this difficulty, we propose a practical method, termed \textit{onlineGPSSM}, that incorporates stochastic variational inference (VI) and online VI with novel formulation. The proposed method mitigates the computational complexity without catastrophic forgetting and also support adaptation to changes in a system and/or a real environments. Furthermore, we present application of onlineGPSSM into the reinforcement learning (RL) of partially observable dynamical systems by integrating onlineGPSSM with Bayesian filtering and trajectory optimization algorithms. Numerical examples are presented to demonstrate applicability of the proposed method.
関連論文
- 潜在想像によるパラメータ化行動空間の学習モデルベースRL
- チャンク単位のモデルベース方策最適化モデルベースRL
- モデルベース強化学習における動力学変化下でのリプレイ保持の特性評価モデルベースRL
- モデルベース強化学習のための償却低ランク適応モデルベースRL
- 変化点対応ワールドモデル:動力学シフトの検出と古いリプレイの忘却による回復モデルベースRL
- RENEW: 選好から世界モデルの学習とモデル悪用の修復を目指してモデルベースRL
