A new multiresolution analysis (wavelet) assisted reinforcement learning (RL) based control strategy that can effectively deal with both multiscale disturbances in processes and the lack of process models. The application of wavelet aided RL based controller represents a paradigm shift in the control of large scale stochastic dynamic systems of which the control problem is a subset. The control strategy is termed a WRL-RbR controller. The WRL-RbR controller is tested on a multiple-input-multiple-output (MIMO) Chemical Mechanical Planarization (CMP) process of wafer fabrication for which process model is available. Results show that the RL controller outperforms EWMA based controllers for low autocorrelation. The new controller also performs quite well for strongly autocorrelated processes for which the EWMA controllers are known to fail. Convergence analysis of the new breed of WRL-RbR controller is presented. Further enhancement of the controller to deal with model free processes and for inputs coming from spatially distributed environments are also addressed.
Ganesan, Rajesh; Das, Tapas K.; and Ramachandran, Kandethody M., "System for multiresolution analysis assisted reinforcement learning approach to run-by-run control" (2010). USF Patents. 467.
University of South Florida