LGJul 25, 2015

True Online Emphatic TD($λ$): Quick Reference and Implementation Guide

arXiv:1507.07147v11 citations
Originality Synthesis-oriented
AI Analysis

This is an incremental guide for researchers implementing reinforcement learning algorithms, focusing on a specific combination of existing methods.

The paper provides an implementation guide for true online emphatic TD(λ), a model-free temporal-difference algorithm that combines emphasis and true-online ideas for long-term predictions with linear function approximation and off-policy training.

This document is a guide to the implementation of true online emphatic TD($λ$), a model-free temporal-difference algorithm for learning to make long-term predictions which combines the emphasis idea (Sutton, Mahmood & White 2015) and the true-online idea (van Seijen & Sutton 2014). The setting used here includes linear function approximation, the possibility of off-policy training, and all the generality of general value functions, as well as the emphasis algorithm's notion of "interest".

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes