sgoodfriend's picture
PPO playing procgen-starpilot-easy from https://github.com/sgoodfriend/rl-algo-impls/tree/21ee1ab96a186676e5ed2f8c3185902f7c7bca7a
b1aa132
raw
history blame
255 Bytes
source benchmarks/train_loop.sh
ALGOS="ppo"
ENVS="HalfCheetahBulletEnv-v0 AntBulletEnv-v0 HopperBulletEnv-v0 Walker2DBulletEnv-v0"
BENCHMARK_MAX_PROCS="${BENCHMARK_MAX_PROCS:-3}"
train_loop $ALGOS "$ENVS" | xargs -I CMD -P $BENCHMARK_MAX_PROCS bash -c CMD