A Reinforcement Learning Approach to job-shop Scheduling

By Thomas G. Dietterich. 1995

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

Learning to Run Heuristics in Tree Search (2017, methodology): “For instance, deep learning can help tune gradient descent [Andrychowicz et al., 2016], reinforcement learning is used for job-shop scheduling [Zhang and Dietterich, 1995], and classification is used for selecting an algorithm for QBF subproblems [Samulowitz and Memisevic, 2007].”
Reinforcement Learning: A Survey (1996, methodology): “…networks for Q-learning; Watkins (1989) used CMAC for Q-learning; Tesauro (1992, 1995) used backpropagation for learning the value function in backgammon (described in Section 8.1); Zhang and Dietterich (1995) used backpropagation and TD((cid:21)) to learn good strategies for job-shop scheduling.”
Infinite-Horizon Policy-Gradient Estimation (2001, background): “…empirical successes in a number of different domains, including learning to play checkers (Samuel, 1959), backgammon (Tesauro, 1992, 1994), and chess (Baxter, Tridgell, & Weaver, 2000), job-shop scheduling (Zhang & Dietterich, 1995) and dynamic channel allocation (Singh & Bertsekas, 1997).”
Transfer Learning for Reinforcement Learning Domains: A Survey (2009, background): “…tasks which other machine learning techniques are either unable or ill-equipped to address (e.g., TDGammon Tesauro 1994, job shop scheduling Zhang and Dietterich 1995, elevator control Crites and B rto 1996, helicopter control Ng et al. 2004, marble maze control Bentivegna et al. 2004,…”
Imitation and Reinforcement Learning in Agents with Heterogeneous Actions (2001, methodology): “…include robot motion planning, computer animation, the adaptation of new controllers to environments where existing controllers have been successfully employed, and acceleration of the learning of schedule repair strategies by RL (Zhang & Dietterich, 1995) through observation of a human expert.”
Finite time bounds for sampling based fitted value iteration (2005, background): “During the last decade, reinforcement learning (RL) algorithms have been successfully applied to a number of difficult control problems, such as job-shop scheduling (Zhang and Dietterich, 1995), backgammon (Tesauro, 1995), elevator control (Crites and Barto, 1997), machine maintenance (Mahadevan et ”
A unifying framework for computational reinforcement learning theory (2009, background): “…Littman 1994], elevator dispatching [Crites and Barto 1996], discrete optimization problems such as job-shop scheduling and Boolean satisfiability [Zhang and Dietterich 1995; Boyan and Moore 2000; Lagoudakis and Littman 2001], channel allocation [Singh and Bertsekas 1997], algorithm selection…”
Solving Mixed Integer Programs Using Neural Networks (2020, background): “Some of the earliest works in this area are Zhang and Dietterich (1995), Moll et al. (1999), Boyan and Moore (1997).”
Multiobjective Reinforcement Learning: A Comprehensive Overview (2015, background): “, linear VFA [96], [97] and nonlinear VFA [9], [98], [99].”
Unsupervised Real-Time Control Through Variational Empowerment (2017, unknown): “…[Li et al., 2009, Tsitsik-lis and Van Roy, 1999, 2001], targeted marketing [Abe et al., 2004], learning to play games [Silver et al., 2016, 2007, Tesauro, 1994], predictive maintainance [Gosavi, 2004], process automation [Zhang and Dietterich, 1995] or electrical power systems [Ernst et al., 2005].”
A Supervised Machine Learning Approach to Variable Branching in Branch-And-Bound (2014, background): “Machine learning has also been used to learn search heuristics able to efficiently explore the search space in specific contexts, such as special instances of combinatorial problems [21,24], and protein structure prediction [20].”
A comparison of direct and model-based reinforcement learning (1997, methodology): “The real world successes of reinforcement learning that we are aware of have been in problems where good or perfect models were available, and in fact the results were often only demonstrated on simulations using those models (Tesauro, 1995; Zhang and Dietterich, 1995; Crites and Barto, 1996).”
Evolutionary Function Approximation for Reinforcement Learning (2006, methodology): “The server job scheduling task is quite different from traditional scheduling tasks Zhang and Dietterich (1995); Zweben and Fox (1998).”