The expected-outcome model of two-player games

By B. Abramson. 1990

Subfields: Evaluation & Benchmarks

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Evaluation & Benchmarks

1. Tom Everitt
2. David Krueger
3. Pieter Abbeel
4. Sergey Ten
5. Yang Gao
6. Miljan Martic
7. Thanard Kurutach
8. Jan Leike

Citations in the corpus

• Scalable agent alignment via reward modeling: a research direction (2018, methodology): “A model-based RL agent learns an explicit model of the environment which it can use with a planning algorithm such as Monte Carlo tree search (Abramson, 1987; Kocsis & Szepesvári, 2006).”
• Mastering Atari Games with Limited Data (2021, methodology): “Monte-Carlo Tree Search [1, 33, 34, 14], or MCTS, is a heuristic search algorithm.”
• Reinforcement Learning with A* and a Deep Heuristic (2018, methodology): “The strength of A∗ is also its main weakness: when a heuristic is unknown other algorithms are used, most notably Monte Carlo Tree Search (MCTS, Abramson 1987).”