From reinforcement learning to optimal control: a unified framework for sequential decisions

DOI10.1007/978-3-030-60990-0_3OpenAlexW2993197237MaRDI QIDQ2094027

Warren B. Powell

Publication date: 28 October 2022

Full work available at URL: https://arxiv.org/abs/1912.03513

Mathematics Subject Classification ID

Optimal stochastic control (93E20) Optimality conditions for problems involving randomness (49K45) Artificial intelligence (68Txx)

Related Items (1)

A deep real options policy for sequential service region design and timing

Uses Software

• AlphaGo

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• AlphaGo
• Neural network approach to continuous-time direct adaptive optimal control for partially unknown nonlinear systems
• Robust constrained model predictive control using linear matrix inequalities
• Stochastic optimal control. The discrete time case
• A unified framework for stochastic optimization
• Introduction to stochastic control theory
• Rollout algorithms for combinatorial optimization
• Probability and Stochastics
• Multi‐Armed Bandit Allocation Indices
• Approximate Dynamic Programming
• Introduction to Stochastic Search and Optimization
• Optimal Control Theory
• Interpolation based computationally efficient predictive control
• Nonlinear Model Predictive Control: An Introductory Review
• An Adaptive Sampling Algorithm for Solving Markov Decision Processes
• Parameterized Tube Model Predictive Control
• Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems
• Stochastic Control Theory
• Reinforcement Learning and Stochastic Optimization

This page was built for publication: From reinforcement learning to optimal control: a unified framework for sequential decisions