Alert button
Picture for Michael Bowling

Michael Bowling

Alert button

Monitored Markov Decision Processes

Add code
Bookmark button
Alert button
Feb 13, 2024
Simone Parisi, Montaser Mohammedalamen, Alireza Kazemipour, Matthew E. Taylor, Michael Bowling

Viaarxiv icon

Assessing the Interpretability of Programmatic Policies with Large Language Models

Add code
Bookmark button
Alert button
Nov 12, 2023
Zahra Bashir, Michael Bowling, Levi H. S. Lelis

Viaarxiv icon

TacticAI: an AI assistant for football tactics

Add code
Bookmark button
Alert button
Oct 17, 2023
Zhe Wang, Petar Veličković, Daniel Hennes, Nenad Tomašev, Laurel Prince, Michael Kaisers, Yoram Bachrach, Romuald Elie, Li Kevin Wenliang, Federico Piccinini, William Spearman, Ian Graham, Jerome Connor, Yi Yang, Adrià Recasens, Mina Khan, Nathalie Beauguerlange, Pablo Sprechmann, Pol Moreno, Nicolas Heess, Michael Bowling, Demis Hassabis, Karl Tuyls

Figure 1 for TacticAI: an AI assistant for football tactics
Figure 2 for TacticAI: an AI assistant for football tactics
Figure 3 for TacticAI: an AI assistant for football tactics
Figure 4 for TacticAI: an AI assistant for football tactics
Viaarxiv icon

Proper Laplacian Representation Learning

Add code
Bookmark button
Alert button
Oct 16, 2023
Diego Gomez, Michael Bowling, Marlos C. Machado

Viaarxiv icon

Targeted Search Control in AlphaZero for Effective Policy Improvement

Add code
Bookmark button
Alert button
Feb 28, 2023
Alexandre Trudeau, Michael Bowling

Figure 1 for Targeted Search Control in AlphaZero for Effective Policy Improvement
Figure 2 for Targeted Search Control in AlphaZero for Effective Policy Improvement
Figure 3 for Targeted Search Control in AlphaZero for Effective Policy Improvement
Figure 4 for Targeted Search Control in AlphaZero for Effective Policy Improvement
Viaarxiv icon

Settling the Reward Hypothesis

Add code
Bookmark button
Alert button
Dec 20, 2022
Michael Bowling, John D. Martin, David Abel, Will Dabney

Figure 1 for Settling the Reward Hypothesis
Figure 2 for Settling the Reward Hypothesis
Viaarxiv icon

Over-communicate no more: Situated RL agents learn concise communication protocols

Add code
Bookmark button
Alert button
Nov 02, 2022
Aleksandra Kalinowska, Elnaz Davoodi, Florian Strub, Kory W Mathewson, Ivana Kajic, Michael Bowling, Todd D Murphey, Patrick M Pilarski

Figure 1 for Over-communicate no more: Situated RL agents learn concise communication protocols
Figure 2 for Over-communicate no more: Situated RL agents learn concise communication protocols
Figure 3 for Over-communicate no more: Situated RL agents learn concise communication protocols
Figure 4 for Over-communicate no more: Situated RL agents learn concise communication protocols
Viaarxiv icon

Interpolating Between Softmax Policy Gradient and Neural Replicator Dynamics with Capped Implicit Exploration

Add code
Bookmark button
Alert button
Jun 04, 2022
Dustin Morrill, Esra'a Saleh, Michael Bowling, Amy Greenwald

Figure 1 for Interpolating Between Softmax Policy Gradient and Neural Replicator Dynamics with Capped Implicit Exploration
Viaarxiv icon

Efficient Deviation Types and Learning for Hindsight Rationality in Extensive-Form Games: Corrections

Add code
Bookmark button
Alert button
May 24, 2022
Dustin Morrill, Ryan D'Orazio, Marc Lanctot, James R. Wright, Michael Bowling, Amy R. Greenwald

Figure 1 for Efficient Deviation Types and Learning for Hindsight Rationality in Extensive-Form Games: Corrections
Figure 2 for Efficient Deviation Types and Learning for Hindsight Rationality in Extensive-Form Games: Corrections
Figure 3 for Efficient Deviation Types and Learning for Hindsight Rationality in Extensive-Form Games: Corrections
Figure 4 for Efficient Deviation Types and Learning for Hindsight Rationality in Extensive-Form Games: Corrections
Viaarxiv icon

Should Models Be Accurate?

Add code
Bookmark button
Alert button
May 22, 2022
Esra'a Saleh, John D. Martin, Anna Koop, Arash Pourzarabi, Michael Bowling

Figure 1 for Should Models Be Accurate?
Viaarxiv icon