Elevator Group Control Using Multiple Reinforcement Learning Agents

By Robert H. Crites, Andrew Barto. 1998

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 Multiagent Communication with Backpropagation (2016, background): “Practical examples include elevator control [3] and sensor networks [5]; communication is also important for success in robot soccer [25].”
A survey and critique of multiagent deep reinforcement learning (2018, methodology): “4 Before DQN, many approaches used neural networks for representing the Q-value function [74], such as Neural Fitted Q-learning [268] and NEAT+Q [351].”
Reinforcement Learning in Continuous State and Action Spaces (2012, unknown): “Examples include Backgammon (Tesauro, 1992, 1994, 1995), robotics (Anderson, 1989; Lin, 1993; Touzet, 1997; Coulom, 2002) and elevator dispatching (Crites and Barto, 1996, 1998).”
Large-Scale Order Dispatch in On-Demand Ride-Hailing Platforms: A Learning and Planning Approach (2018, background): “In resource management, this problem is investigated by both the community of operation research [18] and reinforcement learning [5, 11].”
Lyapunov Design for Safe Reinforcement Learning (2003, background): “Examples include such diverse problems as backgammon playing (Tesauro 1994, 1995), job-shop scheduling (Zhang and Dietterich, 1996), elevator dispatching (Crites and Barto, 1998), and option pricing (Tsitsiklis and Van Roy, 1999).”
Dynamic Safe Interruptibility for Decentralized Multi-Agent Reinforcement Learning (2017, background): “In many real-world applications, multi-agent systems use independent learners that do not explicitly coordinate [6, 21].”
A Survey of Learning in Multiagent Environments: Dealing with Non-Stationarity (2017, background): “However, it has been applied with some success in different multiagent scenarios (Tan, 1993; Sen et al., 1994; Crites and Barto, 1998).”
Natural actor-critic algorithms (2009, background): “It is not unusual in practical applications for such a simulator to be available when an explicit transition-probability model of the sort suitable for use by dynamic or linear programming is not [64, 32].”
A Review of Safe Reinforcement Learning: Methods, Theories, and Applications (2024, unknown): “For example, TD learning is used to solve problems including backgammon playing [200], [201], job-shop scheduling and elevator group control [202]; a stochastic approximation algorithm with RL properties is utilized to solve pricing options for ﬁnancial derivatives in two-player and zero-sum games…”
Multi-agent Reinforcement Learning: An Overview (2010, unknown): “In resource management, the agents form a cooperative team, and they can be one of the following: • Managers of resources, as in [33].”
Multiobjective Reinforcement Learning: A Comprehensive Overview (2015, background): “However, the empirical results of successful RL applications using nonlinear VFA commonly lack rigorous theoretical analysis.”
Hysteretic q-learning :an algorithm for decentralized reinforcement learning in cooperative multi-agent teams (2007, background): “Besides the theoretical examinations, several successful applications of decentralized RL have been reported, like in the control of a group of elevators [14] or in the task of multi-robot box-pushing [15].”
Policy evaluation with temporal differences: a survey and comparison (2015, background): “Policy-iteration-based reinforcement learning has yielded impressive applications in robot soccer (Riedmiller and Gabel, 2007), elevator control (Crites and Barto, 1998) and game-playing such as Checkers (Samuel, 1959), Backgammon (Tesauro, 1994) and Go (Gelly and Silver, 2008).”
Convex Optimization: Algorithms and Complexity (2015, unknown): “The outcomes {Yt(a)} are drawn i.i.d. over time from an unknown probability distribution P (·|a, s) ∈ P(Y), where P(Y) denotes the set of probability distributions on (Borel) subsets of Y. Model 2 (Contextual Bandit) Define a contextual bandit to be a tuple 〈S,A,Y, PS , P, r〉 where • S is the set…”