Model-Based Exploration in Monitored Markov Decision Processes

Authors: Kazemipour, Alireza, Parisi, Simone, Taylor, Matthew E., Bowling, Michael

Subject Terms: Computer Science - Machine Learning

Access URL: http://arxiv.org/abs/2502.16772

Agency Is Frame-Dependent

Authors: Abel, David, Barreto, André, Bowling, Michael, Dabney, Will, Dong, Shi, Hansen, Steven, Harutyunyan, Anna, Khetarpal, Khimya, Lyle, Clare, Pascanu, Razvan, Piliouras, Georgios, Precup, Doina, Richens, Jonathan, Rowland, Mark, Schaul, Tom, Singh, Satinder

Subject Terms: Computer Science - Artificial Intelligence

Access URL: http://arxiv.org/abs/2502.04403

On the Interplay Between Sparsity and Training in Deep Reinforcement Learning

Authors: Davelouis, Fatima, Martin, John D., Bowling, Michael

Subject Terms: Computer Science - Machine Learning, Computer Science - Artificial Intelligence

Access URL: http://arxiv.org/abs/2501.16729

A Method for Evaluating Hyperparameter Sensitivity in Reinforcement Learning

Authors: Adkins, Jacob, Bowling, Michael, White, Adam

Subject Terms: Computer Science - Machine Learning, Computer Science - Artificial Intelligence

Access URL: http://arxiv.org/abs/2412.07165

Real-Time Recurrent Learning using Trace Units in Reinforcement Learning

Authors: Elelimy, Esraa, White, Adam, Bowling, Michael, White, Martha

Subject Terms: Computer Science - Machine Learning, Computer Science - Artificial Intelligence

Access URL: http://arxiv.org/abs/2409.01449

Meta-Gradient Search Control: A Method for Improving the Efficiency of Dyna-style Planning

Authors: Burega, Bradley, Martin, John D., Kapeluck, Luke, Bowling, Michael

Subject Terms: Computer Science - Machine Learning, Computer Science - Artificial Intelligence

Access URL: http://arxiv.org/abs/2406.19561

Beyond Optimism: Exploration With Partially Observable Rewards

Authors: Parisi, Simone, Kazemipour, Alireza, Bowling, Michael

Subject Terms: Computer Science - Machine Learning

Access URL: http://arxiv.org/abs/2406.13909

Monitored Markov Decision Processes

Authors: Parisi, Simone, Mohammedalamen, Montaser, Kazemipour, Alireza, Taylor, Matthew E., Bowling, Michael

Subject Terms: Computer Science - Machine Learning

Access URL: http://arxiv.org/abs/2402.06819

Assessing the Interpretability of Programmatic Policies with Large Language Models

Authors: Bashir, Zahra, Bowling, Michael, Lelis, Levi H. S.

Subject Terms: Computer Science - Artificial Intelligence, Computer Science - Programming Languages, Computer Science - Software Engineering

Access URL: http://arxiv.org/abs/2311.06979

TacticAI: an AI assistant for football tactics

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

Subject Terms: Computer Science - Machine Learning, Computer Science - Multiagent Systems, Statistics - Machine Learning

Access URL: http://arxiv.org/abs/2310.10553

Proper Laplacian Representation Learning

Authors: Gomez, Diego, Bowling, Michael, Machado, Marlos C.

Subject Terms: Computer Science - Machine Learning, Computer Science - Artificial Intelligence

Access URL: http://arxiv.org/abs/2310.10833

Learning not to Regret

Authors: Sychrovský, David, Šustr, Michal, Davoodi, Elnaz, Bowling, Michael, Lanctot, Marc, Schmid, Martin

Subject Terms: Computer Science - Computer Science and Game Theory, Computer Science - Machine Learning

Access URL: http://arxiv.org/abs/2303.01074

Targeted Search Control in AlphaZero for Effective Policy Improvement

Authors: Trudeau, Alexandre, Bowling, Michael

Subject Terms: Computer Science - Artificial Intelligence, Computer Science - Machine Learning

Access URL: http://arxiv.org/abs/2302.12359

Settling the Reward Hypothesis

Authors: Bowling, Michael, Martin, John D., Abel, David, Dabney, Will

Subject Terms: Computer Science - Artificial Intelligence, Computer Science - Machine Learning, Mathematics - Statistics Theory

Access URL: http://arxiv.org/abs/2212.10420

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

Authors: Kalinowska, Aleksandra, Davoodi, Elnaz, Strub, Florian, Mathewson, Kory W, Kajic, Ivana, Bowling, Michael, Murphey, Todd D, Pilarski, Patrick M

Subject Terms: Computer Science - Multiagent Systems, Computer Science - Computation and Language, Computer Science - Human-Computer Interaction

Access URL: http://arxiv.org/abs/2211.01480

The Alberta Plan for AI Research

Authors: Sutton, Richard S., Bowling, Michael, Pilarski, Patrick M.

Subject Terms: Computer Science - Artificial Intelligence, Computer Science - Machine Learning

Access URL: http://arxiv.org/abs/2208.11173

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

Authors: Morrill, Dustin, Saleh, Esra'a, Bowling, Michael, Greenwald, Amy

Subject Terms: Computer Science - Machine Learning, Computer Science - Artificial Intelligence, Statistics - Machine Learning

Access URL: http://arxiv.org/abs/2206.02036

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

Authors: Morrill, Dustin, D'Orazio, Ryan, Lanctot, Marc, Wright, James R., Bowling, Michael, Greenwald, Amy R.

Subject Terms: Computer Science - Computer Science and Game Theory, Computer Science - Artificial Intelligence

Access URL: http://arxiv.org/abs/2205.12031

Should Models Be Accurate?

Authors: Saleh, Esra'a, Martin, John D., Koop, Anna, Pourzarabi, Arash, Bowling, Michael

Subject Terms: Computer Science - Machine Learning, Computer Science - Artificial Intelligence, Statistics - Machine Learning

Access URL: http://arxiv.org/abs/2205.10736

Student of Games: A unified learning algorithm for both perfect and imperfect information games

Authors: Schmid, Martin, Moravcik, Matej, Burch, Neil, Kadlec, Rudolf, Davidson, Josh, Waugh, Kevin, Bard, Nolan, Timbers, Finbarr, Lanctot, Marc, Holland, G. Zacharias, Davoodi, Elnaz, Christianson, Alden, Bowling, Michael

Source: Science Advances 9, eadg3256 (2023)

Subject Terms: Computer Science - Artificial Intelligence, Computer Science - Computer Science and Game Theory, Computer Science - Machine Learning

Access URL: http://arxiv.org/abs/2112.03178