reproduce problem: env is running!

[wwxFromTju]

Dear mhauskn:

I want to use tensorflow to reproduce this experiment. But I find some problem.The most import is agent and env use network to connect, so when I training the policy, the env is runing! And when I use network to infer the action(need some time to cal), but the env is also runing!

so how to control the env waiting the agent?

Thx!

[mhauskn]

The environment should wait for the agent to choose its next action. There is a flag --no-sync which disables this and requires the agents to make decisions in real time. Make sure that you don't run the simulator with this flag.

…

On Sun, Mar 18, 2018 at 12:43 AM, xiaowei Wang ***@***.***> wrote: Dear mhauskn: I want to use tensorflow to reproduce this experiment. But I find some problem.The most import is agent and env use network to connect, so when I training the policy, the env is runing! And when I use network to infer the action(need some time to cal), but the env is also runing! so how to control the env waiting the agent? Thx! — You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub <#32>, or mute the thread <https://github.com/notifications/unsubscribe-auth/AABNOaQPkL8VlZXep_GZldNAzTv-zfOTks5tfhA2gaJpZM4SvGpF> .

[wwxFromTju]

Hi, when I want to look this effect, I find the simulator isn't run, but I can get some log in term.

such as: I run my code, agent is stop in the simulator, but I can get diff log (I print the state info, action and so on), what happen?

[wwxFromTju]

maybe render module have some issue, other module is fine.