Approximate Dynamic Programming

By Sanjiban Choudhury. Encyclopedia of Machine Learning and Data Mining, 2018

484 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/dd781ba01e48b4dee8ae840c5cff5dae70c88479

How researchers see this paper

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

Citations in the corpus

Reinforcement learning for control: Performance, stability, and deep approximators (2018, background): “The works of de Farias and Roy (2003); Wang et al. (2014); Beuchat et al. (2016) devise LP approaches to ADP by formulating linear optimization problems whose solution corresponds to the solution of the optimal control problem (2)-(3) for γ ∈ (0 , 1).”
Value Iteration Adaptive Dynamic Programming for Optimal Control of Discrete-Time Nonlinear Systems (2016, unknown): “Value iteration algorithms are a class of the most important iterative ADP algorithms [43]–[49].”
Learning to Play in a Day: Faster Deep Reinforcement Learning by Optimality Tightening (2016, background): “Reinforcement learning (Bertsekas & Tsitsiklis, 1996; Powell, 2011; Sutton & Barto, 1998; Kaelbling et al., 1996) studies these problems and algorithms which learn policies to make decisions so as to maximize a reward signal from the environment.”
Deep Reinforcement Learning: An Overview (2017, methodology): “1 We refer readers to materials for further study: reinforcement learning (Sutton and Barto, 2017; Szepesv´ari, 2010; Bertsekas, 2012; Powell, 2011; Bertsekas and Tsitsiklis, 1996; Puterman, 2005; Littman, 2015; Kaelbling et al., 1996); deep learning (LeCun et al., 2015; Goodfellow et al., 2016;…”
Residential Demand Response Using Reinforcement Learning (2010, unknown): “Knowledge of the values of z(t) and p(t) during the current period allows us to use the post-decision form of the Bellman equation [19].”
Covering models and optimization techniques for emergency response facility location and planning: a review (2011, unknown): “Maxwell et al. (2009a) developed a simulation model to analyze the performance of a current redeployment policy and incorporated this simulation model into an approximate dynamic programming procedure to obtain allocation policies.”
Interpretable Optimal Stopping (2018, unknown): “ADP has been extensively studied in the operations research community since the mid-1990s as a solution technique for Markov decision processes (Powell 2007, Van Roy 2002).”
Towards Generalization and Simplicity in Continuous Control (2017, methodology): “For a large class of methods based on dynamic programming (including Q-learning, SARSA, approximate policy and value iteration), linear function approximation has guaranteed convergence and error bounds, while non-linear function approximation is known to diverge in many cases [29, 30, 31, 32].”