Towards lifelong learning of Recurrent Neural Networks for control design
This addresses the need for adaptive plant models in control design to avoid catastrophic forgetting and capacity saturation, but it is incremental as it builds on existing methods for a specific domain.
The paper tackles the problem of adapting recurrent neural network models for control systems when new information or system changes occur, proposing a lifelong learning method inspired by Moving Horizon Estimators and demonstrating it on a simulated chemical plant benchmark.
This paper proposes a method for lifelong learning of Recurrent Neural Networks, such as NNARX, ESN, LSTM, and GRU, to be used as plant models in control system synthesis. The problem is significant because in many practical applications it is required to adapt the model when new information is available and/or the system undergoes changes, without the need to store an increasing amount of data as time proceeds. Indeed, in this context, many problems arise, such as the well known Catastrophic Forgetting and Capacity Saturation ones. We propose an adaptation algorithm inspired by Moving Horizon Estimators, deriving conditions for its convergence. The described method is applied to a simulated chemical plant, already adopted as a challenging benchmark in the existing literature. The main results achieved are discussed.