Meta-Learning Guarantees for Online Receding Horizon Learning Control
arXiv:2010.11327
Abstract
In this paper we provide provable regret guarantees for an online meta-learning receding horizon control algorithm in an iterative control setting. We consider the setting where, in each iteration the system to be controlled is a linear deterministic system that is different and unknown, the cost for the controller in an iteration is a general additive cost function and there are affine control input constraints. By analysing conditions under which sub-linear regret is achievable, we prove that the meta-learning online receding horizon controller achieves an average of the dynamic regret for the controller cost that is with the number of iterations . Thus, we show that the worst regret for learning within an iteration improves with experience of more iterations, with guarantee on rate of improvement.
arXiv commentThe proof of the method in this paper is incorrect. The correct method, which is different from this paper is given in "online learning for predictive control with provable regret guarantees": arXiv:2111.15041
References in corpus (14)
- A Simple Neural Attentive Meta-Learner
- RL: Fast Reinforcement Learning via Slow Reinforcement Learning
- Learning to reinforcement learn
- Global Convergence of Policy Gradient Methods for the Linear Quadratic Regulator
- Meta-Learning with Implicit Gradients
- Learning to Optimize
- Online Meta-Learning
- Online convex optimization for cumulative constraints
- Improper Learning for Non-Stochastic Control
- Online Control with Adversarial Disturbances
- Online Optimal Control with Linear Dynamics and Predictions: Algorithms and Regret Analysis
- Logarithmic Regret for Online Control
- Provable Guarantees for Gradient-Based Meta-Learning
- A Stochastic View of Optimal Regret through Minimax Duality