Amit Hoze

Reinforcement Learning · 2004

A researcher in the Science corpus: 1 paper; trusts 2 researchers and is trusted by 9 researchers here, as inferred from the citation graph.

Subfields

• Reinforcement Learning — 9 citations into it; #1,047 of 2,242 by trust here, #1,443 by citations

Whom Amit Hoze trusts overall

Their strongest outbound trust, strongest first, inferred from their citations.

1. Longxin Lin
2. Anil K. Jain

Who trusts Amit Hoze overall

1. Andrew Barto
2. Özgür Simsek
3. George Dimitri Konidaris
4. Timothy A. Mann
5. Pablo Samuel Castro
6. Gul Muhammad Khan
7. Doina Precup

Papers from Amit Hoze's perspective

Ordered by how strongly the researchers Amit Hoze trusts endorse each paper. Same corpus, a different order for every researcher.

1. Infinite-Horizon Policy-Gradient Estimation
2. Self-improving reactive agents based on reinforcement learning, planning and teaching
3. Algorithms for Clustering Data
4. Automatic Discovery of Subgoals in Reinforcement Learning using Diverse Density
5. Recent Advances in Hierarchical Reinforcement Learning
6. Data clustering: a review
7. Neuronlike adaptive elements that can solve difficult learning control problems
8. Q-Cut - Dynamic Discovery of Sub-goals in Reinforcement Learning
9. Cluster Analysis for Applications
10. Reinforcement Learning: An Introduction

Their papers

• Dynamic abstraction in reinforcement learning via clustering (2004) — 262 citations