|
|
|
|
|
|
by pu_pe
96 days ago
|
|
|
I meant trivial in the sense it's a solved problem, I'm sure it still costs a non-negligible amount of money to train it. See for example the chess transformer built by DeepMind a couple of years ago which I referred to in a sibling comment [1]. [1] https://arxiv.org/abs/2402.04494 |
|
|
I admit, my knowledge of reinforcement learning is a bit outdated so it seemed to me that it was unattainable for a non-specialized model to train efficiently on something like chess, which has a huge state space.