Joe Booth

use env.monitor - it will periodically output video and also will record the stats and prep for uploading to OpenAi Gym after env = gym.make(env_name) add `env.monitor.start('/tmp/dqn', force=True) ` and...

OK - the problem is with the T4 GPU - I've been able to get it running with the default GPU. It would be good to figure this out as...

here you go: ``` # nvidia-xconfig: X configuration file generated by nvidia-xconfig # nvidia-xconfig: version 410.72 Section "ServerLayout" Identifier "Layout0" Screen 0 "Screen0" InputDevice "Keyboard0" "CoreKeyboard" InputDevice "Mouse0" "CorePointer" EndSection...

@ervteng - I have a GTX 1080 locally. How many training steps per second do you see? running `nvidia-smi` shows that it is using the GPU so I wass wrong:...

@kwea123 obstacle tower installs a special version of ml-agents that doesn't specify tensorflow in its' install requirements file. obstacle tower does need tensorflow to run. The normal ml-agents specifies tensorflow...

I have an i7-8700k @ 3.7GHz which has 6 processors / 12 cores A big help to performance would be to support multiple instances of the environment within the Unity...

@psarras - i was able to get it running on my windows machine. I followed the GCP tutorial. You don't need to install dopamine as the tutorial has you running...

I followed instructions for MSI - https://github.com/j8lp/atari-py

@ervteng that sounds good - I think the main thing is to have it clear in the guide

I was able to get large-scale-curiosity + Obstacle Challenge working up to about 32 agents * make sure `worker_id` is unique for each instance * `timeout_wait=6000` * add a `sleep(2)`...