This week, Brown University hosts the Multi-disciplinary Conference on Reinforcement Learning and Decision Making (RLDM), bringing more than 500 thought leaders to PVD and demonstrating Brown’s continued status as a leading center for RL research and study bit.ly/3thLVm3

🔺 Climb and uncover the secrets of a pyramid in this new #PICO8 Celeste mod! Made in under a week for the CCMAMJ, featuring 🎵 by RubyRed. #gamedev #celeste meepmoop.itch.io/rosetta

A draft of the Alberta Plan for AI Research came out today on arXiv. :-) arxiv.org/abs/2208.11173

Some impulsive #pico8 #speedcubing :D Uses Heise's KB layout with the minimalism of qCube #gamedev

Harvest fish as a penguin in this turn-based dungeon crawler! Made in 48h for #LudumDare52 🐧 #pico8 #gamedev meepmoop.itch.io/water-under-th…

Pico Playtime: Water Under the Bridge by Kris D. for #Pico8 is a turn-based, dungeon crawlin' fish-'em-up made for #LudumDare52. Outmanoeuvre aquatic enemies to catch fish to feed your penguin family. youtu.be/tt5vCNasuAQ

Check out the #Celeste Classic Advent Calendar- a *daily* #PICO8 Celeste mod for twelve days, organized by RubyRed! evergreengames.github.io/cchristmas/

🗻 Climb a mountain in Canada 🇨🇦 in this #PICO8 Celeste mod! Made in ~72h for the CC Advent Calendar. #gamedev #celeste meepmoop.itch.io/true-north evergreengames.github.io/cchristmas/

Learning about the history of RL at the birthplace of RL from the founders of RL at the first RL_Conference! What a privilege!

Now that RL_Conference is over (and what a success it was!), it's time to start thinking about the next one. If you haven't heard yet, RLC is going north. We'll be organizing RLC'25 in Edmonton! I'm very excited about that and look forward to seeing everyone there.

Kicked off my blog with an in-depth guide to Star Battle—my favorite logic puzzle! Here's hoping it improves accessibility and gets more people into it 😃 kris.pengy.ca/starbattle

If you are looking to conduct research full-time on the foundations of AI, and • you have read the RL textbook and done the exercises, • you agree with the Alberta Plan for AI Research, • you already have a PhD, • you are open to spending some time in Edmonton, then the

"In the Beginning, ML was RL". Andrew Barto gave RLC 2024 an amazing overview of the intertwined history of ML and RL (Link below)

RLC will be held at the Univ. of Alberta, Edmonton, in 2025. I'm happy to say that we now have the conference's website out: rl-conference.cc/index.html We'll continue to update it, and the CFP will be out soon, but the relevant dates are already there. RL_Conference University of Alberta

The original RL algorithms, inspired by natural learning, were online and incremental—they were streaming in the sense that they learned from each increment of experience as it happened, then discarded it, never to be processed again. The streaming algorithms were simple and

Meet the recipients of the 2024 ACM A.M. Turing Award, Andrew G. Barto and Richard S. Sutton! They are recognized for developing the conceptual and algorithmic foundations of reinforcement learning. Please join us in congratulating the two recipients! bit.ly/4hpdsbD

Andrej Karpathy Andrej Karpathy I think it would be good to distinguish RL as a problem from the algorithms that people use to address RL problems. This would allow us to discuss if the problem is with the algorithms, or if the problem is with posing a problem as an RL problem. 1/x

Reinforcement learning 🧠 on robots 🤖 can’t stay in simulation forever. My new post explores why direct, on-hardware learning matters and how we also need smarter mechanical design to enable it. kris.pengy.ca/designforlearn…

I wrote a thing. Current humanoid robotics startups are not ready for the messiness of the world. Even if they succeed at everything they believe they need to do, it would still be insufficient for making useful robots. More here: khurramjaved.com/not_ready_for_…