Online Gaussian Process State-Space Model: Learning and Planning for Partially Observable Dynamical Systems
This work addresses the problem of efficient online learning for partially observable dynamical systems, offering incremental improvements in computational resource usage.
The paper tackles the computational inefficiency of learning Gaussian process state-space models (GP-SSM) from sequential data by proposing an online method called onlineGPSSM, which reduces computational complexity without catastrophic forgetting and supports adaptation to system changes, with numerical examples demonstrating its applicability.
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.