ianma

maybe we can store experience as a tuple like (s_t, a, r, s_t_1, t), terminal state will not be store in experience replay if use this pattern. usually t is...

I have met a similar problem when I use TF-TRT and saved_model_cli to convert a saved model. These two methods failed when using Embedding layer. https://stackoverflow.com/questions/67085221/failed-to-use-tf-trt-when-using-tf-keras-layers-embedding

@Byron309 I can run the code with Tensorflow-gpu 1.14. Before running the train script, I set `export GPU=0` and `export CUDA_VISIBLE_DEVICES=0`.

The cmd in setup_all.sh may be out-of-date. You can change `g++ -std=c++11 -shared coref_kernels.cc -o coref_kernels.so -fPIC ${TF_CFLAGS[@]} ${TF_LFLAGS[@]} -O2 -D_GLIBCXX_USE_CXX11_ABI=0` into `g++ -std=c++11 -shared coref_kernels.cc -o coref_kernels.so -fPIC ${TF_CFLAGS[@]}...

`g++ -std=c++11 -shared coref_kernels.cc -o coref_kernels.so -fPIC ${TF_CFLAGS[@]} ${TF_LFLAGS[@]} -O2 -D_GLIBCXX_USE_CXX11_ABI=0` is line 13 in the [setup_all.sh](https://github.com/kentonl/e2e-coref/blob/master/setup_all.sh) I didn't meet this error before. I think you can make some modifications...

报名！ 马跃 BOT5会员：否 清华推荐 清华的小迷弟！