I thought that applying AI on 1v1 competitive pokemon would be a fun and educational experience on POMDPs and trying out reward free models on a problem that would be classically treated as a RL problem. This was only possible thanks to a lot of foundational work from the open-source community and last year's competitive pokemon NeurIPS track https://pokeagent.github.io/track1.html - they laid out the plugins to connect policy models to pokemon showdown for live play and evaluation.
I have already finished training the standard discriminative auto-regressive architectures by imitation learning on player actions, compared it with previous baselines set in the study. I want to match or exceed the best prior model Kakuna @ 142M params, but in a limited budget. JEPA style world models are showing promise when conditioned on actions [1] and frontier research on JEPA with trajectory straightening [2] shows that improved planning is natural outcome of improved representations.
If any good research ideas come out of this exploration then even better!
I inherited a stake in a pyridine derivatives chemical plant - while I do not know much about chemical feedstocks and the chemical supply chain, I am trying to help the current partner optimize their yields and reduce losses across multiple stages of reactions across the feedstock and reagents. It is quite similar to hardware design and electrical engineering than I thought.
I have also taken an interest in learning distributed paradigms like MPI and am using it on my own cluster of rPis
I have already finished training the standard discriminative auto-regressive architectures by imitation learning on player actions, compared it with previous baselines set in the study. I want to match or exceed the best prior model Kakuna @ 142M params, but in a limited budget. JEPA style world models are showing promise when conditioned on actions [1] and frontier research on JEPA with trajectory straightening [2] shows that improved planning is natural outcome of improved representations.
If any good research ideas come out of this exploration then even better!
Currently fork with my models: https://github.com/sooham/metamon (under checkpoints) Orginal source for pokeagents: https://github.com/metamon/metamon
[1] https://arxiv.org/abs/2603.19312 [2] https://arxiv.org/html/2603.12231v1
A good primer on world models from Welch Labs - one of my favourite ML youtubers: https://www.youtube.com/watch?v=kYkIdXwW2AE