Few Shot System Identification for Reinforcement Learning

TL;DR

This paper introduces a framework for few-shot system identification in reinforcement learning, enabling adaptive modeling of system dynamics with uncertainties to improve control performance and sample efficiency.

Contribution

It proposes a probabilistic approach using variational inference to quickly adapt system models for different instances within the same dynamics class in model-based RL.

Findings

The framework accurately predicts system trajectories under uncertainty.

It enhances the robustness of RL control across varied system instances.

The method achieves high sample efficiency in control tasks.

Abstract

Learning by interaction is the key to skill acquisition for most living organisms, which is formally called Reinforcement Learning (RL). RL is efficient in finding optimal policies for endowing complex systems with sophisticated behavior. All paradigms of RL utilize a system model for finding the optimal policy. Modeling dynamics can be done by formulating a mathematical model or system identification. Dynamic models are usually exposed to aleatoric and epistemic uncertainties that can divert the model from the one acquired and cause the RL algorithm to exhibit erroneous behavior. Accordingly, the RL process sensitive to operating conditions and changes in model parameters and lose its generality. To address these problems, Intensive system identification for modeling purposes is needed for each system even if the model dynamics structure is the same, as the slight deviation in the model parameters can render the model useless in RL. The existence of an oracle that can adaptively predict the rest of the trajectory regardless of the uncertainties can help resolve the issue. The target of this work is to present a framework for facilitating the system identification of different instances of the same dynamics class by learning a probability distribution of the dynamics conditioned on observed data with variational inference and show its reliability in robustly solving different instances of control problems with the same model in model-based RL with maximum sample efficiency.