ELF
ELF copied to clipboard
pytorch
ELF: a platform for game research with AlphaGoZero/AlphaZero reimplementation
Hi, When working on a sub-branch of Olivier Teytaud's branch called "newtasks" (which uses the ELF framework for any abstract game), we stumbled on a possible GPU configuration error on...
I fixed dim but still problem with copy of tensor in src_py/elf/utils_elf.py(191)copy_from()
Hi Guys... Any plans to rewrite the code to take advantage of the new features in Python 3.7 GCC 8.2 CUDA 10 CUDNN 7.4 NCCL 2.3.7 Thank you so much
Using two-gtp: [https://www.mankier.com/1/gogui-twogtp](https://www.mankier.com/1/gogui-twogtp) **System Spec:** 150GB RAM TESLA V100 GPU After 2.5 games, using the following settings: ./gtp.sh ~/v1.bin --gpu 0 --num_block 20 --dim 224 --mcts_puct 1.5 --batchsize 2 --mcts_rollout_per_batch...
Hi, I've tried to run the python based environment from `scripts/elfgames/adaptor`. I tried to run it as `game=client model_file=model python server.py` but get the following error: ``` (elf) pawni@host:~/ELF/scripts/elfgames/adaptor$ game=client...
I'm trying to train for 9x9 board using just a few self plays just to see the whole process (selfplay -> training NN using self-play result -> selfplaying using new...
Hello, We are trying to modify your framework so that it could be used for checkers. Could you please tell us where we should look? Where do you use your...
After try to modify the q_min_size=200 ,q_max_size=300 and num_reader=50,and have trained 90000 games.But the save_0.bin is not updated. We want to know why it is not updated. We also found...
There is quite a lot of discussion about the training, promotion, number of games, etc... about leelaZ on github and discord. Last time you answered that it took ELF 2.5...
