Learning to compete, coordinate, and cooperate in repeated games using reinforcement learning
By Jacob William Crandall, Michael A. Goodrich. 2011
54 citations recorded by the source corpus.
Subfields: Artificial Intelligence, Management Science and Operations Research
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
- Shimon Whiteson
- Jakob N. Foerster
- Pablo Hernandez-Leal
- Igor Mordatch
- Sergey Levine
- Pieter Abbeel
- Stefano V. Albrecht
- Chelsea Finn
In Management Science and Operations Research
- Shimon Whiteson
- Pablo Hernandez-Leal
- Jakob N. Foerster
- Pieter Abbeel
- Igor Mordatch
- Tim Baarslag
- Michael Kaisers
- Enrique Munoz de Cote
Citations in the corpus
- Learning with Opponent-Learning Awareness (2017, background): “A similar idea underlies M-Qubed, [10], which balances best-response, cautious and optimistic learning biases.”
- A Survey of Learning in Multiagent Environments: Dealing with Non-Stationarity (2017, methodology): “M-Qubed (Max or Minimax Q-learning) (Crandall and Goodrich, 2011) is a RL algorithm designed for two-player repeated games.”
- Playing repeated games with large language models (2023, unknown): “We then present details from the human participant study outlined above.”
- Learning to Interact with a Human Partner (2015, background): “On the other hand, M-Qubed [8] and Sarsa [20] usually learn to cooperate with each other, but they require thousands of interactions to do so.”