(5/5) Perhaps I'm overlooking something-open to your insights 😀

(4/5) However, what we see in DeepSeek's formulation is that 1) there is no sequence of actions, and 2) the reference policy remains the same.

I don't see the credit assignment mechanism from future rewards to current actions in this formulation, which is the key factor in RL.

(3/5) Because this objective is difficult to compute (there are two distributions from two different policies involved) a constrain on how far these two policies can be is included so we can just "ignore" this mismatch.

(2/5) In TRPO and PPO, you maximize the expected sum of advantages over a sequence of actions as a way to optimize policy improvement steps.

*generalize

Great book. I also enjoyed it a lot.

Thanks! We introduce inductive bias at different levels. For instance, we refined the centrality encoder to implicitly capture atom hybridization. We have other examples in the paper, and many others that we hope to publish soon 😉

Same here! Thanks :)

Thanks a lot!

I'm working on improving molecular GNN models by adding inductive bias and integrating different data modalities. We recently presented part of our work in a workshop at ICML last July: arxiv.org/abs/2405.14837

Thanks a lot!

Hi, just arrived here. Nice to see this starter pack. Im also doing some research in drug design and I would love to be inluded there as well. Thanks!

Great initiative! I'd love to be there as well