Skip to content

Instantly share code, notes, and snippets.

@vwxyzjn
Created June 11, 2020 17:24
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save vwxyzjn/2d66ff396741e5b9038012a1deb48062 to your computer and use it in GitHub Desktop.
Save vwxyzjn/2d66ff396741e5b9038012a1deb48062 to your computer and use it in GitHub Desktop.
Reproduction of PPO
docker run -d --cpuset-cpus="0" -e WANDB=xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx vwxyzjn/cleanrl:latest python ppo_atari_visual.py --gym-id BeamRiderNoFrameskip-v4 --total-timesteps 10000000 --wandb-project-name cleanrl.benchmark --wandb-entity cleanrl --prod-mode --capture-video --seed 1
docker run -d --cpuset-cpus="1" -e WANDB=xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx vwxyzjn/cleanrl:latest python ppo_atari_visual.py --gym-id BeamRiderNoFrameskip-v4 --total-timesteps 10000000 --wandb-project-name cleanrl.benchmark --wandb-entity cleanrl --prod-mode --capture-video --seed 2
docker run -d --cpuset-cpus="2" -e WANDB=xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx vwxyzjn/cleanrl:latest python ppo_atari_visual.py --gym-id QbertNoFrameskip-v4 --total-timesteps 10000000 --wandb-project-name cleanrl.benchmark --wandb-entity cleanrl --prod-mode --capture-video --seed 1
docker run -d --cpuset-cpus="3" -e WANDB=xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx vwxyzjn/cleanrl:latest python ppo_atari_visual.py --gym-id QbertNoFrameskip-v4 --total-timesteps 10000000 --wandb-project-name cleanrl.benchmark --wandb-entity cleanrl --prod-mode --capture-video --seed 2
docker run -d --cpuset-cpus="4" -e WANDB=xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx vwxyzjn/cleanrl:latest python ppo_atari_visual.py --gym-id SpaceInvadersNoFrameskip-v4 --total-timesteps 10000000 --wandb-project-name cleanrl.benchmark --wandb-entity cleanrl --prod-mode --capture-video --seed 1
docker run -d --cpuset-cpus="5" -e WANDB=xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx vwxyzjn/cleanrl:latest python ppo_atari_visual.py --gym-id SpaceInvadersNoFrameskip-v4 --total-timesteps 10000000 --wandb-project-name cleanrl.benchmark --wandb-entity cleanrl --prod-mode --capture-video --seed 2
docker run -d --cpuset-cpus="6" -e WANDB=xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx vwxyzjn/cleanrl:latest python ppo_atari_visual.py --gym-id PongNoFrameskip-v4 --total-timesteps 10000000 --wandb-project-name cleanrl.benchmark --wandb-entity cleanrl --prod-mode --capture-video --seed 1
docker run -d --cpuset-cpus="7" -e WANDB=xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx vwxyzjn/cleanrl:latest python ppo_atari_visual.py --gym-id PongNoFrameskip-v4 --total-timesteps 10000000 --wandb-project-name cleanrl.benchmark --wandb-entity cleanrl --prod-mode --capture-video --seed 2
docker run -d --cpuset-cpus="8" -e WANDB=xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx vwxyzjn/cleanrl:latest python ppo_atari_visual.py --gym-id BreakoutNoFrameskip-v4 --total-timesteps 10000000 --wandb-project-name cleanrl.benchmark --wandb-entity cleanrl --prod-mode --capture-video --seed 1
docker run -d --cpuset-cpus="9" -e WANDB=xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx vwxyzjn/cleanrl:latest python ppo_atari_visual.py --gym-id BreakoutNoFrameskip-v4 --total-timesteps 10000000 --wandb-project-name cleanrl.benchmark --wandb-entity cleanrl --prod-mode --capture-video --seed 2
for seed in {1..2}
do
(sleep 0.3 && nohup xvfb-run -a python ppo_atari_visual.py \
--gym-id BeamRiderNoFrameskip-v4 \
--total-timesteps 10000000 \
--wandb-project-name cleanrl.benchmark \
--wandb-entity cleanrl \
--prod-mode \
--capture-video \
--seed $seed
) >& /dev/null &
done
for seed in {1..2}
do
(sleep 0.3 && nohup xvfb-run -a python ppo_atari_visual.py \
--gym-id QbertNoFrameskip-v4 \
--total-timesteps 10000000 \
--wandb-project-name cleanrl.benchmark \
--wandb-entity cleanrl \
--prod-mode \
--capture-video \
--seed $seed
) >& /dev/null &
done
for seed in {1..2}
do
(sleep 0.3 && nohup xvfb-run -a python ppo_atari_visual.py \
--gym-id SpaceInvadersNoFrameskip-v4 \
--total-timesteps 10000000 \
--wandb-project-name cleanrl.benchmark \
--wandb-entity cleanrl \
--prod-mode \
--capture-video \
--seed $seed
) >& /dev/null &
done
for seed in {1..2}
do
(sleep 0.3 && nohup xvfb-run -a python ppo_atari_visual.py \
--gym-id PongNoFrameskip-v4 \
--total-timesteps 10000000 \
--wandb-project-name cleanrl.benchmark \
--wandb-entity cleanrl \
--prod-mode \
--capture-video \
--seed $seed
) >& /dev/null &
done
for seed in {1..2}
do
(sleep 0.3 && nohup xvfb-run -a python ppo_atari_visual.py \
--gym-id BreakoutNoFrameskip-v4 \
--total-timesteps 10000000 \
--wandb-project-name cleanrl.benchmark \
--wandb-entity cleanrl \
--prod-mode \
--capture-video \
--seed $seed
) >& /dev/null &
done
for seed in {1..2}
do
(sleep 0.3 && nohup xvfb-run -a python ppo_continuous_action.py \
--gym-id Reacher-v2 \
--total-timesteps 2000000 \
--wandb-project-name cleanrl.benchmark \
--wandb-entity cleanrl \
--prod-mode \
--capture-video \
--seed $seed
) >& /dev/null &
done
for seed in {1..2}
do
(sleep 0.3 && nohup xvfb-run -a python ppo_continuous_action.py \
--gym-id Pusher-v2 \
--total-timesteps 2000000 \
--wandb-project-name cleanrl.benchmark \
--wandb-entity cleanrl \
--prod-mode \
--capture-video \
--seed $seed
) >& /dev/null &
done
for seed in {1..2}
do
(sleep 0.3 && nohup xvfb-run -a python ppo_continuous_action.py \
--gym-id Thrower-v2 \
--total-timesteps 2000000 \
--wandb-project-name cleanrl.benchmark \
--wandb-entity cleanrl \
--prod-mode \
--capture-video \
--seed $seed
) >& /dev/null &
done
for seed in {1..2}
do
(sleep 0.3 && nohup xvfb-run -a python ppo_continuous_action.py \
--gym-id Striker-v2 \
--total-timesteps 2000000 \
--wandb-project-name cleanrl.benchmark \
--wandb-entity cleanrl \
--prod-mode \
--capture-video \
--seed $seed
) >& /dev/null &
done
for seed in {1..2}
do
(sleep 0.3 && nohup xvfb-run -a python ppo_continuous_action.py \
--gym-id InvertedPendulum-v2 \
--total-timesteps 2000000 \
--wandb-project-name cleanrl.benchmark \
--wandb-entity cleanrl \
--prod-mode \
--capture-video \
--seed $seed
) >& /dev/null &
done
for seed in {1..2}
do
(sleep 0.3 && nohup xvfb-run -a python ppo_continuous_action.py \
--gym-id HalfCheetah-v2 \
--total-timesteps 2000000 \
--wandb-project-name cleanrl.benchmark \
--wandb-entity cleanrl \
--prod-mode \
--capture-video \
--seed $seed
) >& /dev/null &
done
for seed in {1..2}
do
(sleep 0.3 && nohup xvfb-run -a python ppo_continuous_action.py \
--gym-id Hopper-v2 \
--total-timesteps 2000000 \
--wandb-project-name cleanrl.benchmark \
--wandb-entity cleanrl \
--prod-mode \
--capture-video \
--seed $seed
) >& /dev/null &
done
for seed in {1..2}
do
(sleep 0.3 && nohup xvfb-run -a python ppo_continuous_action.py \
--gym-id Swimmer-v2 \
--total-timesteps 2000000 \
--wandb-project-name cleanrl.benchmark \
--wandb-entity cleanrl \
--prod-mode \
--capture-video \
--seed $seed
) >& /dev/null &
done
for seed in {1..2}
do
(sleep 0.3 && nohup xvfb-run -a python ppo_continuous_action.py \
--gym-id Walker2d-v2 \
--total-timesteps 2000000 \
--wandb-project-name cleanrl.benchmark \
--wandb-entity cleanrl \
--prod-mode \
--capture-video \
--seed $seed
) >& /dev/null &
done
for seed in {1..2}
do
(sleep 0.3 && nohup xvfb-run -a python ppo_continuous_action.py \
--gym-id Ant-v2 \
--total-timesteps 2000000 \
--wandb-project-name cleanrl.benchmark \
--wandb-entity cleanrl \
--prod-mode \
--capture-video \
--seed $seed
) >& /dev/null &
done
for seed in {1..2}
do
(sleep 0.3 && nohup xvfb-run -a python ppo_continuous_action.py \
--gym-id Humanoid-v2 \
--total-timesteps 2000000 \
--wandb-project-name cleanrl.benchmark \
--wandb-entity cleanrl \
--prod-mode \
--capture-video \
--seed $seed
) >& /dev/null &
done
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment