Neural networks for self-learning control systems

By Derrick Nguyen, Bernard Widrow. 1990

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Reinforcement Learning

Citations in the corpus

Learning Continuous Control Policies by Stochastic Value Gradients (2015, background): “If a differentiable environment model is available, one can link together the policy, model, and reward function to compute an analytic policy gradient by backpropagation of reward along a trajectory [18, 11, 6, 9].”
Model-Ensemble Trust-Region Policy Optimization (2018, neutral): “Although many previous studies have shown promising results on relatively simple domains (Nguyen & Widrow, 1990; Schmidhuber & Huber, 1991; Jordan & Rumelhart, 1992; Gal et al., 2016), so far their applications on more challenging domains have either required a combination with model-free…”
Temporal Difference Models: Model-Free Deep RL for Model-Based Control (2018, methodology): “…learning has been ongoing for decades, with techniques such as synthetic experience generation (Sutton, 1990), partial model-based backpropagation (Nguyen & Widrow, 1990; Heess et al., 2015), and layering model-free learning on the residuals of model-based estimation (Chebotar et al., 2017) being…”
A comprehensive review for industrial applicability of artificial neural networks (2003, methodology): “prediction of paper cure in the papermaking industry [39], controller steering backup truck [85], and modeling of plate”
γ-Models: Generative Temporal Difference Learning for Infinite-Horizon Prediction (2020, unknown): “…of target values for temporal difference learning (Buckman et al., 2018; Feinberg et al., 2018), leveraging model gradients for backpropagation (Nguyen & Widrow, 1990; Jordan & Rumelhart, 1992; Heess et al., 2015), and incorporating model-based planning without explicitly predicting future…”
On-line learning algorithms for locally recurrent neural networks (1999, background): “However, if a general temporal processing is needed, two main gradient-based learning approaches exist for recurrent networks [24], [25], [36]: Backpropagation through time (BPTT) [1], [5], [7], [24], [36], [46] and real-time recurrent learning (RTRL) [2], [23], [24], [27], [28], [36], [38], [49], [”
Cocaine and Chest Pain (1992, unknown): “Neural networks research has spread through almost every field of science, covering areas as different as character recognition [1] [2] [3], medicine [4] [5] [6], speech recognition and synthesis [7] [8], image processing [9] [10], robotics [11] [12] and control systems [13] [14].”
An Introduction to Deep Reinforcement Learning (2018, unknown): “gradient by backpropagation of rewards along trajectories (Nguyen and Widrow, 1990).”
Optimal control by least squares support vector machines (2001, methodology): “For example, Nguyen and Widrow (1990) applied backpropagation to the problem of backing up a trailer±truck based on a neural network emulator for the plant. In Saerens, Renders, and Bersini (1993) a full static state feedback controller has been studied in the context of optimal control, thereby rel”
Residual Policy Learning (2018, methodology): “These methods often ﬁrst learn a dynamics model and then use this dynamics model to simulate experience [6, 7, 8] or compute gradients for model-free updates [9, 10].”