Michael Pang

Also a quick note about question 12: you can prove that with b blue and r red balls and 2 urns, the optimal answer is to put 1 blue in...

Here's an elementary solution to question 38: Let p_i be the probability of reaching n before 0 when starting from i. p_0=0 and p_n=1 and by linearity of expectation, p_i=.5p_{i-1}+.5p_{i+1}...

Yes! The boolean array is a better way of implementing the "hash table" since you have a perfect hash function. It's the same idea as what I meant by "hash...

Hey @benediamond , thanks for commenting! Btw I'm pushing more optimizations to https://github.com/Akababa/chess-alpha-zero/blob/opts/src/chess_zero/agent/player_chess.py now. It looks like it's working well. I didn't train for 100,000 steps anyway (the first time...

yes, I think I did the flipping stuff correctly [here](https://github.com/Akababa/chess-alpha-zero/blob/opts/src/chess_zero/worker/optimize.py#L196), but would really appreciate if you could take a quick look to see if it checks out from your point...

Yeah that's always a worry in the back of my mind (hence the paranoid asserts). I'm a little confused by the conversation though, is there already a bug found in...

Doesn't the DeepMind input actually use an extra plane to encode the side to move? The main reason I did this was for fun, and also it *might* make the...

But why is there a need to flip the policy if you are feeding in the side to move? Yes that was before I read that part of the paper,...

That might be true especially at the beginning, before the model has the chance to learn the rules of chess. However I think we are doing something similar with the...

Yeah I agree that's unclear. I don't even know how they came up with 4629 possible moves.