Maximilian Weichart
@mweichart.bsky.social
Optimism in the face of uncertainty https://maximilian-weichart.de/
📣 Please share: We invite submissions to the 29th International Conference on Artificial Intelligence and Statistics (#AISTATS 2026) and welcome paper submissions at the intersection of AI, machine learning, statistics, and related areas. [1/3]
See you next Monday! www.meetup.com/data-science...
Data Science goes Tampere: iSchool Special , Mon, Sep 22, 2025, 3:30 PM | Meetup
Dear all, We are very pleased to confirm another excuse to travel to a beautiful place (or to log on via Zoom and miss half the fun). We have an action-packed Meetup that
meetup.com
📢 Deadline extended! Submit your work to EWRL — now accepting papers until June 3rd AoE. This year, we're also offering a fast track for papers accepted at other conferences ⚡ Check the website for all the details: euro-workshop-on-reinforcement-learning.github.io/ewrl18/
Today we concluded our first R1 Reinforcement Learning meetup where I presented and we discussed the paper on AssistanceZero (by @cassidylaidlaw.bsky.social et al.) If you're interesting in joining & talking about RL check out the meetup 💡 max-we.github.io/R1/
R1: Reinforcement Learning Meetup
max-we.github.io
Interested in RL? I'm planning to assemble a new online meetup, focused on reinforcement learning paper discussions. You can sign up, and as soon as enough people are interested, you'll get an invitation. More information and registration: max-we.github.io/R1/
R1: Reinforcement Learning Meetup
max-we.github.io
Open-sourced my implementation of AlphaZero and various other MCTS policies to play Tetris. In contrast to other Tetris-agents, this implementation does *not* rely on observation- or action-space simplification. It trains an agent with the same information a human has. github.com/Max-We/alpha...
GitHub - Max-We/alphazero-tetris: An implementation of AlphaZero and MCTS with neural networks for Tetris
An implementation of AlphaZero and MCTS with neural networks for Tetris - Max-We/alphazero-tetris
github.com
🥳 50k score achieved, TetrisZero is working! Here's the viewer-site with a replay (actually, the replay became so long that the site is lagging a bit, lol). Full details on the algorithm will follow, once I evaluate it against AlphaZero... max-we.github.io/tetris-zero/
Tetris Rollout Viewer
max-we.github.io
It's getting there! Target is a score of 50k, currently about 10k.
W&B sweeps is a really nice way of hyperparameter-searching. Didn't see a lot of people talk about it, but it makes the process really nicely streamlined + visualized. Essentially, you just need a config-file with the parameters to try, and it's ready to go docs.wandb.ai/guides/sweeps/
Sweeps
Hyperparameter search and model optimization with W&B Sweeps
docs.wandb.ai
I found this via Scholar Inbox today. These are detailed, clear and understandable explanations + exercises to learn with. Thank you, great work!
Jonas Hübotter@jonhue.bsky.social · 2y agoI'm very excited to share notes on Probabilistic AI that I have been writing with @arkrause.bsky.social 🥳 arxiv.org/pdf/2502.05244 These notes aim to give a graduate-level introduction to probabilistic ML + sequential decision-making. I'm super glad to be able to share them with all of you now!
Working on debugging RL algorithms such as AlphaZero is hard, especially when the codebase uses just-in-time-compiled JAX. So I created a replay-viewer which visualizes an episode with all the policy statistics for a personal project. Will be open-sourced once I finish my new algorithm!
Is it normal to thank ChatGPT in the Acknowledgements of your paper nowadays? lol arxiv.org/pdf/2301.01379
Excited to share that today our paper recommender platform www.scholar-inbox.com has reached 20k users! We hope to reach 100k by the end of the year.. Lots of new features are being worked on currently and rolled out soon.
