Cuz in my case, I have to load the model first before init the env. Thanks.
Can you guys make the change to your evaluator to delay the start of env by 20 seconds? like in env.sh
if [ -z "$2" ] then ENV_FILENAME="./ObstacleTower/obstacletower.x86_64" fi wait 20 touch otc_out.json xvfb-run --auto-servernum --server-args='-screen 0 640x480x24' $ENV_FILENAME --port $ENV_PORT > /dev/null 2&>1 &
Due to the structure of my tensorflow code, I need to load the python libraries and model first before create the environment in the agent. Is it possible for our host to change the way environment pod is launched in evaluation scenarios?