Reinforcement Learning and Dynamic Programming Using Function Approximators

By Lucian Busoniu, Robert Babuška, B. Schutter, Damien Ernst. 2010

922 citations recorded by the source corpus.

Subfields: Computational Theory and Mathematics, Reinforcement Learning

How researchers see this paper

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

In Computational Theory and Mathematics

In Reinforcement Learning

Citations in the corpus

Reinforcement Learning in Healthcare: A Survey (2019, background): “Other fundamental issues in RL research include but are not limited to the credit assignment problem [14], [27], the sampel/space/time complexity [28], [29], function approximation [30], [31], safety [32], [33], robustness [34], [35], and”
Reinforcement learning in robotics: A survey (2013, background): “It offers a larger set of applicable tools ranging from adaptive discretizations (Buşoniu et al., 2010) and function approximation approaches (Sutton and Barto, 1998) to macro-actions or options (Barto and Mahadevan, 2003; Hart and Grupen, 2011).”
Continuous Doubly Constrained Batch Reinforcement Learning (2021, background): “TCDC is a L∞ contraction under standard conditions that suffice for the ordinary Bellman operator to be contractive [3, 6, 8, 56].”
Batch Mode Reinforcement Learning based on the Synthesis of Artificial Trajectories (2012, background): “…mode RL problems over large or continuous spaces combine value or policy iteration schemes from the Dynamic Programming (DP) theory (Bellman 1957) with function approximators (e.g., radial basis functions, neural networks, etc.) representing (state-action) value functions (Busoniu et al. 2010).”
Evolutionary Dynamics of Multi-Agent Learning: A Survey (2015, methodology): “A recent extensive overview of function approximation methods for reinforcement learning is provided by Busoniu et al. (2010).”
Regularization in reinforcement learning (2011, methodology): “[2005] who devise tree-based methods to represent the value function, and Buşoniu et al. [2010b] who use Fuzzy rule set-based FA in the inner loop of AVI.”
Reinforcement Learning for Primary care e Appointment Scheduling (2017, background): “Such algorithms acquire experience to perform a task from trial and error [31] and improve online performance through a balance between exploration and exploitation of the environment with which they interact [31].”
Online Multi-Task Learning for Policy Gradient Methods (2014, methodology): “Cart-Pole: The cart-pole (CP) system has been used extensively as a benchmark for evaluating RL algorithms (Buşoniu et al., 2010).”
Approximate real-time optimal control based on sparse Gaussian process models (2014, neutral): “[21].”
Cooperative and Distributed Reinforcement Learning of Drones for Field Coverage (2018, methodology): “…UAVs are identical, and operated in the same environment, and have identical sets of states and actions: S 1 = S 2 = ... = S m , and The state space and action space set of each agent should be represented as discrete ﬁnite sets approximately, to guarantee the convergence of the RL algorithm [33].”
Reinforcement Learning in Continuous State and Action Spaces (2012, methodology): “For general introductions to reinforcement learning from varying perspectives, we refer to the books by Bertsekas and Tsitsiklis (1996) and Sutton and Barto (1998) and the more recent books by Bertsekas (2007), Powell (2007), Szepesvári (2010) and Buşoniu et al (2010).”
Safe Policy Search for Lifelong Reinforcement Learning with Sublinear Regret (2015, methodology): “Cart Pole: The cart-pole (CP) has been used extensively as a benchmark for evaluating RL methods (Busoniu et al., 2010).”