Philip Amortila

A Distributional Analysis of Sampling-Based Reinforcement Learning Algorithms

Bellemare Marc-Emmanuel

We present a distributional approach to theoretical analyses of reinforcement learning algorithms for constant step-sizes. We demonstrate it… (voir plus)s effectiveness by presenting simple and unified proofs of convergence for a variety of commonly-used methods. We show that value-based methods such as TD(

2020-06-02

Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics (publié)

doi.org

proceedings.mlr.press

Learning Graph Weighted Models on Pictures

Philip Amortila

Guillaume Rabusseau

Graph Weighted Models (GWMs) have recently been proposed as a natural generalization of weighted automata over strings and trees to arbitrar… (voir plus)y families of labeled graphs (and hypergraphs). A GWM generically associates a labeled graph with a tensor network and computes a value by successive contractions directed by its edges. In this paper, we consider the problem of learning GWMs defined over the graph family of pictures (or 2-dimensional words). As a proof of concept, we consider regression and classification tasks over the simple Bars & Stripes and Shifting Bits picture languages and provide an experimental study investigating whether these languages can be learned in the form of a GWM from positive and negative examples using gradient-based methods. Our results suggest that this is indeed possible and that investigating the use of gradient-based methods to learn picture series and functions computed by GWMs over other families of graphs could be a fruitful direction.

2019-02-03

Proceedings of The 14th International Conference on Grammatical Inference 2018 (publié)

proceedings.mlr.press