Regularization in reinforcement learning

By Csaba Szepesvari, Amir-massoud Farahmand. 2011

52 citations recorded by the source corpus.

Subfields: Computational Theory and Mathematics, Control and Systems Engineering, Statistics and Probability

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 Control and Systems Engineering

In Statistics and Probability

Citations in the corpus

Information-Theoretic Considerations in Batch Reinforcement Learning (2019, background): “(2012); Pires & Szepesvári (2012); Farahmand et al. (2016)), according to our knowledge, fast rate for the minimax algorithm has not been established before: for example, Antos et al.”
Sharing Knowledge in Multi-Task Deep Reinforcement Learning (2020, methodology): “We derive upper confidence bounds for Approximate Value-Iteration (AVI) and Approximate Policy-Iteration (API)2 (Farahmand, 2011) in the MTRL setting, and we extend the approximation error bounds in Maurer et al.”
Regularized Policy Iteration with Nonparametric Function Spaces (2016, methodology): “This paper , alongside its conference (Farahmand et al., 2009b) and the dissertation (Farahmand, 2011b) versions, is the first work that analyzes a nonparametric regularized API algorithm and provides such a strong guarantee for it.”
Iterative Value-Aware Model Learning (2018, methodology): “Value-Aware Model Learning (VAML) is a novel framework for learning the model of the environment in Model-Based Reinforcement Learning (MBRL) [Farahmand et al., 2017a, 2016a]. The conventional approach to model learning in MBRL is based on minimizing some kind of probabilistic loss. A common choice ”
Provably Good Batch Reinforcement Learning Without Great Exploration (2020, result): “We make a few remarks about the comparison between this result and prior related results below: Remark 1 (Comparison with prior API/AVI bounds).”
Boosted Curriculum Reinforcement Learning (2022, methodology): “The use of AVI algorithms in this curriculum RL setting consists in starting from an arbitrary estimate Q 01 (where the subscript indicates the position of the task in the curriculum) and approximating the application of the task-speciﬁc optimal Bellman operator for the current task We assume that t”
Is a Good Representation Sufficient for Sample Efficient Reinforcement Learning? (2019, methodology): “This assumption is crucial in proving polynomial sample complexity guarantee for value iteration type of algorithms (Chen & Jiang, 2019; Farahmand, 2011).”