Reinforcement Learning in an Adaptable Chess Environment for Detecting Human-understandable Concepts

10 November 2022

Papers citing "Reinforcement Learning in an Adaptable Chess Environment for Detecting Human-understandable Concepts"

3 / 3 papers shown

Title
Contrastive Sparse Autoencoders for Interpreting Planning of Chess-Playing Agents Yoann Poupart 34 0 0 06 Jun 2024
Information based explanation methods for deep learning agents -- with applications on large open-source chess models Patrik Hammersborg Inga Strümke 13 1 0 18 Sep 2023
Concept backpropagation: An Explainable AI approach for visualising learned concepts in neural network models Patrik Hammersborg Inga Strümke FAtt 16 0 0 24 Jul 2023