Adaptive critic designs
Danil V. Prokhorov, Donald C. Wunsch · IEEE Transactions on Neural Networks · 1997
We discuss a variety of adaptive critic designs (ACDs) for neurocontrol. These are suitable for learning in noisy, nonlinear, and nonstationary environments. They have common roots as generalizations of dynamic programming for neural reinforcement learning approaches. Our discussion of these origins leads to an explanation of three design families: heuristic dynamic programming, dual heuristic programming, and globalized dual heuristic programming (GDHP). The main emphasis is on DHP and GDHP as advanced ACDs. We suggest two new modifications of the original GDHP design that are currently the only working implementations of GDHP. They promise to be useful for many engineering applications in the areas of optimization and optimal control. Based on one of these modifications, we present a unified approach to all ACDs. This leads to a generalized training procedure for ACDs.
Cited by 1,186 works. doi:10.1109/72.623201
Authors
References
- Dynamic Programming
- Principles of Neurodynamics.
- The Organization of Behavior
- Identification and control of dynamical systems using neural networks
- Beyond Regression : "New Tools for Prediction and Analysis in the Behavioral Sciences
- A Learning Algorithm for Continually Running Fully Recurrent Neural Networks
- Learning to Predict by the Methods of Temporal Differences
- The organization of behavior.
- Beyond regression : new fools for prediction and analysis in the behavioral sciences
- Neuronlike adaptive elements that can solve difficult learning control problems