Marlos C. Machado·Oct 29The Reinforcement Learning Journal is now accepting submissionsI’m very excited about this new phase of the Reinforcement Learning Journal (RLJ), which will now accept submissions on a rolling basis. As…
Marlos C. Machado·Mar 25From Pixels to Place Cells: Where Representation Learning Meets NeuroscienceI have been itching to talk about a paper we put out on bioRxiv last year, and I finally found the time to write about it. This is a…
Marlos C. Machado·Mar 12The Cell Must Go On! AgarCL as an Evaluation Platform for Continual RLContinual learning is becoming more popular, with people from diverse research ideologies promoting it. Naturally, as with everything else…
Marlos C. Machado·Aug 11, 2024Announcing the RLC 2024 Outstanding Paper AwardsThis week, we are having the first-ever Reinforcement Learning Conference (RLC), and I couldn’t be more thrilled. I don’t recall having…
Marlos C. Machado·Apr 29, 2024Proper Laplacian Representation LearningWith ICLR around the corner, I thought I would write about the paper we had accepted there this year. The paper title is “Proper Laplacian…A response icon1A response icon1
Marlos C. Machado·Feb 6, 2024On RLC’s Outstanding Paper AwardsThis post is a reproduction of the post at https://rl-conference.cc/blogs/awards_process.html.
Marlos C. Machado·Jan 21, 2024Looking back at my first 3 years as an Amii fellowI’ve been quiet in the last couple of months because I was busy teaching at the University of Alberta, both an undergraduate and a graduate…
Marlos C. Machado·Jul 14, 2023Deep Laplacian-based Options for Temporally-Extended ExplorationIn this post, summarizing a paper we published at ICML’23, I discuss a very general method that implements the ROD cycle quite effectively.
Marlos C. Machado·Jun 30, 2023The Representation-driven Option Discovery CycleHow should we learn temporal abstractions in reinforcement learning?
Marlos C. Machado·Jun 15, 2023Don’t Panic!Reinforcement learning is full of magical things patiently waiting for our wits to grow sharper