Breeding a diversity of Super Mario behaviors through interactive evolution

By Patrikk D. Sørensen, Jeppeh M. Olsen, Sebastian Risi. 2016

13 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Sociology and Political Science, Reinforcement Learning, 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 Artificial Intelligence

1. Jan Leike
2. Shane Legg
3. Paul Christiano
4. Sergey Levine
5. Miljan Martic
6. Dario Amodei
7. Tom Everitt
8. Tom B. Brown

In Sociology and Political Science

1. Miljan Martic
2. Shane Legg

In Reinforcement Learning

1. Jan Leike
2. Shane Legg
3. Paul Christiano
4. Sergey Levine
5. Dario Amodei
6. Miljan Martic
7. Tom B. Brown
8. Pieter Abbeel

In Evaluation & Benchmarks

1. Miljan Martic
2. Jan Leike
3. Tom B. Brown
4. Shane Legg
5. Ben Goertzel

Citations in the corpus

• Deep Reinforcement Learning from Human Preferences (2017, background): “ürnkranz et al., 2012; Akrour et al., 2014), and optimizing using human preferences in settings other than reinforcement learning (Machwe and Parmee, 2006; Secretan et al., 2008; Brochu et al., 2010; Sørensen et al., 2016). Our algorithm follows the same basic approach as Akrour et al. (2012) and Ak”