Philipp Rohlfshagen

Artificial Intelligence · 2011–2012

A researcher in the Science corpus: 2 papers; trusts 5 researchers and is trusted by 3 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 20 citations into it; #26,253 of 35,345 by trust here, #6,266 by citations
• Reinforcement Learning — 16 citations into it
• Economics and Econometrics — 11 citations into it; #21,036 of 23,481 by trust here, #2,748 by citations
• Game & Decision Theory — 7 citations into it
• Management Science and Operations Research — 6 citations into it

Whom Philipp Rohlfshagen trusts overall

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

1. Levente Kocsis
2. Csaba Szepesvari
3. John R. Koza

Who trusts Philipp Rohlfshagen overall

1. Oriol Vinyals
2. Yuxi Li

Papers from Philipp Rohlfshagen's perspective

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

1. Bandit Based Monte-Carlo Planning
2. Efficient Selectivity and Backup Operators in Monte-Carlo Tree Search
3. Asymptotically efficient adaptive allocation rules
4. Asymptotically Efficient Adaptive Allocation Rules
5. COMPUTING “ELO RATINGS” OF MOVE PATTERNS IN THE GAME OF GO
6. Gambling in a rigged casino: The adversarial multi-armed bandit problem
7. Simulation-Based Approach to General Game Playing (AAAI Conference on Artificial Intelligence)
8. Combining online and offline knowledge in UCT
9. Minimax Policies for Adversarial and Stochastic Bandits
10. Monte-Carlo Planning in Large POMDPs

Their papers

• A Survey of Monte Carlo Tree Search Methods (2012) — 3,443 citations
• Ms Pac-Man versus Ghost Team CEC 2011 competition (2011) — 70 citations