Adaptive Input Estimation In Linear Dynamical Systems With Applications To Learning-from-observations

Abstract

We address the problem of estimating the inputs of a dynamical system from measurements of the system's outputs. To this end, we introduce a novel estimation algorithm that explicitly trades off bias and variance to optimally reduce the overall estimation error. This optimal trade-off is done efficiently and adaptively in every time step. Experimentally, we show that our method often produces estimates with substantially lower error compared to the state-of-the-art. Finally, we consider the more complex *Learning-from-Observations* framework, where an agent should learn a controller from the outputs of an expert's demonstration. We incorporate our estimation algorithm as a building block inside this framework and show that it enables learning controllers successfully.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keycuri2018adaptive

Related papers

• Sample Complexity Of Estimating The Policy Gradient For Nearly Deterministic Dynamical Systems (2019)0.00
• An Efficient, Expressive And Local Minima-free Method For Learning Controlled Dynamical Systems (2017)2.26
• Model-based Reinforcement Learning For Control Under Time-varying Dynamics (2026)0.00
• Optimal Exploration For Model-based RL In Nonlinear Systems (2023)0.00
• Dream To Explore: Adaptive Simulations For Autonomous Systems (2021)0.00
• Lyapunov-based Reinforcement Learning State Estimator (2020)8.09
• Logarithmic Regret For Nonlinear Control (2025)0.00
• RLOC: Neurobiologically Inspired Hierarchical Reinforcement Learning Algorithm For Continuous Control Of Nonlinear Dynamical Systems (2019)0.00