Ken
Ken
Yes. I try google or-tools. It's powerful.
how to reproduce the result for hhblits? it there any solution?
hi guys, how to handle the above issues? do you reproduce the released results.
@soodoshll I meet the similar error. I install the cityflow from the open source. When I run the following code, import cityflow eng = cityflow.Engine("/home/ken/project/CityFlow/examples/roadnet.json") There occurs: interval is required...
It doesn't work. After replacing "roadnet.json" with "config.json", there occurs: cannot open roadnet file loading roadnet file error! load config failed!
Also, in scenario=simple_speaker_listener, this code cannot converge to the result reported in Fig.4. Anyone knows the problem?
@kevin-y-ma @Ah31 Could you reproduce the results. Also, it seem `num_sample = 1` is a bug? i think it should be `num_sample = len(obs_next_n)`?
is rigid.identity trainable during training phage？
Thanks. It works. But it seems the wrapped environment with num_processes=1 is **much slower** than the original gym environment.
I test this program on ubuntu 18.04, cpu=intel i5, 8 CPUs. I compare the running time on CartPole-v1 between standard gym and the wrapped gym. The wrapped gym is much...