davidhershey / feudal_networks

An implementation of FeUdal Networks for Hierarchical Reinforcement Learning as published : https://arxiv.org/abs/1703.01161

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Could you explain how to run it?

wonchul-kim opened this issue · comments

when i run it by typing train.py, i got this:

Executing the following commands:
mkdir -p /tmp/pong
echo /usr/bin/python train.py > /tmp/pong/cmd.sh
kill $( lsof -i:12345 -t ) > /dev/null 2>&1
kill $( lsof -i:12222-12223 -t ) > /dev/null 2>&1
tmux kill-session -t a3c
tmux new-session -s a3c -n ps -d bash
tmux new-window -t a3c -n w-0 bash
tmux new-window -t a3c -n tb bash
tmux new-window -t a3c -n htop bash
sleep 1
tmux send-keys -t a3c:ps 'CUDA_VISIBLE_DEVICES= /usr/bin/python worker.py --log-dir /tmp/pong --env-id PongDeterministic-v4 --num-workers 1 --job-name ps' Enter
tmux send-keys -t a3c:w-0 'CUDA_VISIBLE_DEVICES= /usr/bin/python worker.py --log-dir /tmp/pong --env-id PongDeterministic-v4 --num-workers 1 --job-name worker --task 0 --remotes 1 --policy lstm' Enter
tmux send-keys -t a3c:tb 'tensorboard --logdir /tmp/pong --port 12345' Enter
tmux send-keys -t a3c:htop htop Enter

Use tmux attach -t a3c to watch process output
Use tmux kill-session -t a3c to kill the job
Point your browser to http://localhost:12345 to see Tensorboard

I don't know how tmux works, but there is no error sign.
What did do wrong?

commented

If you have tmux installed, run the "tmux attach - a3c" command and you will drop into a tmux shell. Nothing's wrong, the code is running and if you enter "http://localhost:12345/" in your browser, you can see the progress

I am suffering from the same problem and I don't know what should I do.

It is not easy to install all dependencies. So I made an docker image.
If you have docker environment, can try it using bellow command

sudo docker run -it -v "$(pwd)/log":/tmp cuspymd/feudal-networks