sgoodfriend's picture
PPO playing HalfCheetahBulletEnv-v0 from https://github.com/sgoodfriend/rl-algo-impls/tree/2067e21d62fff5db60168687e7d9e89019a8bfc0
6f3bdf9
raw
history blame
242 Bytes
ALGO="ppo"
ENVS="CartPole-v1 MountainCar-v0 MountainCarContinuous-v0 Acrobot-v1 LunarLander-v2"
BENCHMARK_MAX_PROCS="${BENCHMARK_MAX_PROCS:-3}"
bash scripts/train_loop.sh -a $ALGO -e "$ENVS" | xargs -I CMD -P $BENCHMARK_MAX_PROCS bash -c CMD