System Identification via Meta-Learning in Linear Time-Varying Environments

Abstract

System identification is a fundamental problem in reinforcement learning, control theory and signal processing, and the non-asymptotic analysis of the corresponding sample complexity is challenging and elusive, even for linear time-varying (LTV) systems. To tackle this challenge, we develop an episodic block model for the LTV system where the model parameters remain constant within each block but change from block to block. Based on the observation that the model parameters across different blocks are related, we treat each episodic block as a learning task and then run meta-learning over many blocks for system identification, using two steps, namely offline meta-learning and online adaptation. We carry out a comprehensive non-asymptotic analysis of the performance of meta-learning based system identification. To deal with the technical challenges rooted in the sample correlation and small sample sizes in each block, we devise a new two-scale martingale small-ball approach for offline meta-learning, for arbitrary model correlation structure across blocks. We then quantify the finite time error of online adaptation by leveraging recent advances in linear stochastic approximation with correlated samples.

References in corpus (13)

• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Prototypical Networks for Few-shot Learning
• On First-Order Meta-Learning Algorithms
• Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables
• On the Sample Complexity of the Linear Quadratic Regulator
• Near optimal finite time identification of arbitrary linear dynamical systems
• Unsupervised Meta-Learning for Reinforcement Learning
• Learning Without Mixing: Towards A Sharp Analysis of Linear System Identification
• Finite-Time Error Bounds For Linear Stochastic Approximation and TD Learning
• Learning-based Control of Unknown Linear Systems with Thompson Sampling
• Provable Guarantees for Gradient-Based Meta-Learning
• Least-Squares Temporal Difference Learning for the Linear Quadratic Regulator
• Real-Time Edge Intelligence in the Making: A Collaborative Learning Framework via Federated Meta-Learning