Behold, the beautiful result of downloading NeurIPS 2023 code and running it on MNIST!
27.02.2026 05:00
👍 7
🔁 1
💬 2
📌 0
Behold, the beautiful result of downloading NeurIPS 2023 code and running it on MNIST!
Hillary Clinton: “You have compelled me to testify, fully aware that I have no knowledge that would assist your investigation, in order to distract attention from President Trump’s actions and to cover them up despite legitimate calls for answers”
Just about finished copyediting "Markov Decision Processes and Reinforcement Learning" by Puterman and Chan. Expect it out in June. All chapters of the pre-copyedited version and more are still available at github.com/martyput/MDP.... #RL #OR
Well done Alan and David.
Happy to just have deleted my twitter/x account
But its helpful to students and researchers if you share them.
It takes alot of effort to turn them into a text. I speak from experience.
The bee sting and great expectations
Preprints of ALL chapters of "Markov Decision Processes and Reinforcement Learning" by Puterman and Chan are now posted at github.com/martyput/MDP....
All feedback and typos are greatly appreciated and will impact the final version. Links will be removed when the book is published. #AI #orms
Chapters 1-7 of our forthcoming book “Markov Decision Processes and Reinforcement Learning” by Puterman and Chan can be dowloaded at:
github.com/martyput/MDP....
They cover model foundations, and MDPs. Please share comments and/or typos ASAP.
#orms #AI #ReinforcementLearning
An important point about this site is that if you have deep MDP questions, instead of asking an influencer on twitter, you can ask @martypute.bsky.social which is uh, a serious step up
How to reach them?
Will post details and link to preprint on bluesky asap. I want to get off twitter too.
I hope our forthcoming MDP/RL text fills that gap.
Rick Scott; We'll miss your amazing music and presence in the Vancouver music scene.
youtu.be/nlyRiUIAByM?...
Our textbook on Markov decision processes and reinforcement learning is shortly going to press.
A key philosophy in our new book.
Stay safe
I strongly agree
Congrats Andrew and Rich, well deserved!! apnews.com/article/turi...
A new Trump resort?
Hell no!
In the early part of my career, many said to me: all your work in RL & MDPs will never see applications. They were so wrong...most modern robots are based on RL. And about 1/3rd of the talks at the last INFORMS were on RL and the Bellman equation.
I would like to give a tutorial on MDPs.
Our forthcoming mdp/rl book should help! #rl #orms
Chinese food with family.
I’m planning to attend. Would like to speak about mdps and our new book.
