Portrait de Philip Amortila n'est pas disponible

Philip Amortila

Alumni

Publications

A Distributional Analysis of Sampling-Based Reinforcement Learning Algorithms
Philip Amortila
Doina Precup
Prakash Panangaden
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(
2019-12-31
AISTATS (publié)
doi.org
proceedings.mlr.press
Temporally Extended Metrics for Markov Decision Processes.
Philip Amortila
Bellemare Marc-Emmanuel
Prakash Panangaden
Doina Precup
2018-12-31
SafeAI@AAAI (publié)
dblp.uni-trier.de
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.
2017-12-31
ICGI (publié)
proceedings.mlr.press
proceedings.mlr.press