ppo-Acrobot-v1 / benchmarks /train_loop.sh
sgoodfriend's picture
PPO playing Acrobot-v1 from https://github.com/sgoodfriend/rl-algo-impls/tree/5598ebc4b03054f16eebe76792486ba7bcacfc5c
341188c
raw
history blame
637 Bytes
train_loop () {
local WANDB_TAGS="benchmark_$(git rev-parse --short HEAD) host_$(hostname)"
local algo
local env
local seed
local WANDB_PROJECT_NAME="${WANDB_PROJECT_NAME:-rl-algo-impls-benchmarks}"
local args=()
(( VIRTUAL_DISPLAY == 1)) && args+=("--virtual-display")
local SEEDS="${SEEDS:-1 2 3}"
for algo in $(echo $1); do
for env in $(echo $2); do
for seed in $SEEDS; do
echo python train.py --algo $algo --env $env --seed $seed --pool-size 1 --wandb-tags $WANDB_TAGS --wandb-project-name $WANDB_PROJECT_NAME ${args[@]}
done
done
done
}