Michael T. Matthews

According to our database, Michael T. Matthews authored at least 8 papers between 2018 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2024

Kinetix: Investigating the Training of General Agents through Open-Ended Physics-Based Control Tasks.

Michael T. Matthews, Michael Beukman, Chris Lu, Jakob N. Foerster

CoRR, 2024

JaxLife: An Open-Ended Agentic Simulator.

Chris Lu, Michael Beukman, Michael T. Matthews, Jakob N. Foerster

CoRR, 2024

Policy-Guided Diffusion.

Matthew Thomas Jackson, Michael T. Matthews, Cong Lu, Benjamin Ellis, Shimon Whiteson, Jakob Nicolaus Foerster

RLJ, 2024

Craftax: A Lightning-Fast Benchmark for Open-Ended Reinforcement Learning.

Michael T. Matthews, Michael Beukman, Benjamin Ellis, Mikayel Samvelyan, Matthew Thomas Jackson, Samuel Coward, Jakob Nicolaus Foerster

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Refining Minimax Regret for Unsupervised Environment Design.

Michael Beukman, Samuel Coward, Michael T. Matthews, Mattie Fellows, Minqi Jiang, Michael D. Dennis, Jakob Nicolaus Foerster

Proceedings of the Forty-first International Conference on Machine Learning, 2024

2022

Multi-Modal Fusion by Meta-Initialization.

Matthew Thomas Jackson, Shreshth A. Malik, Michael T. Matthews, Yousuf Mohamed-Ahmed

CoRR, 2022

Hierarchical Kickstarting for Skill Transfer in Reinforcement Learning.

Michael T. Matthews, Mikayel Samvelyan, Jack Parker-Holder, Edward Grefenstette, Tim Rocktäschel

Proceedings of the Conference on Lifelong Learning Agents, 2022

2018

Instructional designers' perspectives on learners' responsibility for learning.

Michael T. Matthews, Stephen C. Yanchar

J. Comput. High. Educ., 2018