Function Approximation

Function approximation aims to represent complex, potentially high-dimensional functions using simpler, computationally tractable models. Current research emphasizes developing novel architectures, such as Kolmogorov-Arnold networks and those incorporating Chebyshev polynomials or path signatures, alongside improved algorithms like those based on optimism principles or two-timescale methods. These advancements are crucial for addressing challenges in diverse fields, including reinforcement learning, contextual bandits, and scientific machine learning, where accurate and efficient function representation is essential for effective modeling and prediction.

Papers

June 2, 2022

Which Explanation Should I Choose? A Function Approximation Perspective to Characterizing Post Hoc Explanations
Tessa Han, Suraj Srinivas, Himabindu Lakkaraju
Line by Line Explanation High Explainability Explanation Method Function Approximation Post Hoc Explanation Local Approximation

May 12, 2022

KASAM: Spline Additive Models for Function Approximation
Heinrich van Deventer, Pieter Janse van Rensburg, Anna Bosman
Catastrophic Forgetting Function Approximation

April 22, 2022

Adaptive Online Value Function Approximation with Wavelets
Michael Beukman, Michael Mitchley, Dean Wookey, Steven James, George Konidaris
Linear Function Approximation Function Approximation Wavelet Based Dimensional State Space Wavelet Base

March 8, 2022

A Complete Characterization of Linear Estimators for Offline Policy Evaluation
Juan C. Perdomo, Akshay Krishnamurthy, Peter Bartlett, Sham Kakade
Reinforcement Learning Linear Function Approximation Function Approximation Linear Estimator Offline Policy Evaluation Complete Characterization Fitted Q Iteration

March 5, 2022

Target Network and Truncation Overcome The Deadly Triad in $Q$-Learning
Zaiwei Chen, John Paul Clarke, Siva Theja Maguluri
Linear Function Approximation Function Approximation Q$ Learning Finite Sample Guarantee Goal Node Balanced Truncation Curiosity Driven Reinforcement Learning

March 2, 2022

Learning Efficiently Function Approximation for Contextual MDP
Orin Levy, Yishay Mansour
LeArning Abstract Supervised Learning Function Approximation Contextual MDPs

February 8, 2022

Independent Policy Gradient for Large-Scale Markov Potential Games: Sharper Rates, Function Approximation, and Game-Agnostic Convergence
Dongsheng Ding, Chen-Yu Wei, Kaiqing Zhang, Mihailo R. Jovanović
Multi Agent Reinforcement Learning Policy Gradient Markov Game Function Approximation Fast Rate Convergence Behavior Markov Potential Game

December 2, 2021

Level set learning with pseudo-reversible neural networks for nonlinear dimension reduction in function approximation
Yuankai Teng, Zhu Wang, Lili Ju, Anthony Gruber, Guannan Zhang
Neural Network High Dimensional Dimensionality Reduction Function Approximation Different Level Dimensional Input Active Subspace

November 23, 2021

The Impact of Data Distribution on Q-learning with Function Approximation
Pedro P. Santos, Diogo S. Carvalho, Alberto Sardinha, Francisco S. Melo
Global Impact Offline Reinforcement Learning Q Learning Dynamic Programming Function Approximation Data Distribution High Entropy

November 12, 2021

Resilient Consensus-based Multi-agent Reinforcement Learning with Function Approximation
Martin Figura, Yixuan Lin, Ji Liu, Vijay Gupta
Multi Agent Reinforcement Learning Actor Critic Algorithm Function Approximation Adversarial Agent Cooperative Agent Byzantine Agent

July 30, 2020

Random Vector Functional Link Networks for Function Approximation on Manifolds
Deanna Needell, Aaron A. Nelson, Rayan Saab, Palina Salanevich, Olov Schavemaker
Neural Network Gradient Based Class Manifold Function Approximation Universal Approximators Layer Neural Network Random Vector Functional Link