Tejan Karmali
Tejan Karmali
I am interested to take this up! From what I interpret, do we require the GPUArray version of the convolutions and pooling in Julia? Please correct me if I am...
Hi Abhijeet! That's a nice idea. We were planning it to name AlphaZero.jl. Suggestions are welcome though :)
How about we initialize them in `src/go.jl`?
This has been fixed in `alphazero` branch
We need to train the model well :)
Good idea. I don't think it would be complex for DP, but we would require some changes in AlphaGo.jl, in order to make it differentiable. `step!` function of Go is...
Yes, I'll get it on GPU. Skipping ahead is possible by not rendering the frams, but I am not sure if that'll improve the training speed. I'll try that.
It'd be great to have a sister package, like what [baselines](https://github.com/openai/baselines) is to [OpenAI Gym](https://github.com/openai/gym), showing off RL algorithms with Gym.jl
Making separate package is useful, for the same reasons mentioned by @v-i-s-h . Any of the framework can be used, but I'll be biased towards Flux ;)
Thanks for pointing out. I tried changing it and running on the examples from model-zoo, and that has difficulty in learning. The gradients vanish due to use of clamp, maybe...