Preben Alstrøm

Reinforcement Learning · 1998–2004

A researcher in the Science corpus: 2 papers; trusts 1 researcher and is trusted by 20 researchers here, as inferred from the citation graph.

Subfields

• Reinforcement Learning — 5 citations into it; #737 of 2,242 by trust here, #1,125 by citations

Whom Preben Alstrøm trusts overall

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

1. G. Tesauro

Who trusts Preben Alstrøm overall

1. Ani Harutyunyan
2. Finale Doshi-Velez
3. Marc G. Bellemare
4. Sam Devlin
5. Aaron Wilson
6. Suvir Mirchandani
7. George Dimitri Konidaris
8. Michail G. Lagoudakis
9. Alan Fern
10. H. Braun

Papers from Preben Alstrøm's perspective

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

1. TD-Gammon, a Self-Teaching Backgammon Program, Achieves Master-Level Play
2. Planning and Acting in Partially Observable Stochastic Domains
3. Temporal Difference Learning and TD-Gammon
4. Temporal credit assignment in reinforcement learning
5. Learning from Demonstration
6. Residual Algorithms: Reinforcement Learning with Function Approximation
7. Learning internal representations by error propagation
8. Eligibility Traces for Off-Policy Policy Evaluation
9. ON THE LIKELIHOOD THAT ONE UNKNOWN PROBABILITY EXCEEDS ANOTHER IN VIEW OF THE EVIDENCE OF TWO SAMPLES
10. Temporal abstraction in reinforcement learning

Their papers

• COMPLEXITY AND CRITICALITY (2004) — 510 citations
• Learning to Drive a Bicycle Using Reinforcement Learning and Shaping (1998)