Dynamic Programming and Optimal Control. Volume 1

By David K. Smith. 1996

Subfields: Reinforcement Learning, Mathematical Optimization

How researchers see this paper

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

In Reinforcement Learning

In Mathematical Optimization

Citations in the corpus

Actor-Mimic: Deep Multitask and Transfer Reinforcement Learning (2015, background): “Hence, the sequence of policies generated by the algorithm converges almost surely to a unique ﬁxed point π ∗ from Lemma 1 and the Contraction Mapping Theorem Bertsekas (1995).”
Boosting the Actor with Dual Critic (2017, methodology): “(1995) provide details in deriving the linear programming form of the Bellman optimality equation.”
The Uncertainty Bellman Equation and Exploration (2017, methodology): “To show this we use three essential properties of the Bellman operator for a fixed policy (Bertsekas, 2005).”
Deep Multi-Agent Reinforcement Learning with Relevance Graphs (2018, methodology): “When the environment dynamics (transition probabilities and reward function) are available, this task can be solved using policy iteration [2].”
Reverse Curriculum Generation for Reinforcement Learning (2017, background): “sampling from the above distributions ⇢ 0 , ⇡ ✓ , P) and use them to improve the current policy [29, 30, 31].”
Online Optimal Control with Linear Dynamics and Predictions: Algorithms and Regret Analysis (2019, methodology): “The special case of LQ tracking problems is in the following form, where Q > 0 , R > 0 , and P e is the solution to the algebraic Riccati equation with respect to Q, R [52].”
An online primal-dual method for discounted Markov decision processes (2016, methodology): “It can also be viewed as a discrete-time analog of stochastic optimal control [4], [5].”
Sample-Optimal Parametric Q-Learning Using Linearly Additive Features (2019, background): “For instance, Tsitsiklis & Van Roy (1997); Nedić & Bertsekas (2003); Lagoudakis & Parr (2003); Melo et al. (2008); Parr et al. (2008); Sutton et al. (2009); Lazaric et al. (2012); Tagorti & Scherrer (2015) and Maei et al.”
Minimax-Optimal Off-Policy Evaluation with Linear Function Approximation (2020, methodology): “Regression methods are often used to ﬁt value functions and to satisfy the Bellman equation (Bertsekas et al., 1995; Sutton & Barto, 2018).”