PPO playing MicrortsAttackShapedReward-v1 from https://github.com/sgoodfriend/rl-algo-impls/tree/587a52bc38901314c7c1b5c6892acf9315796cf3
a1df559
ALGO="ppo" | |
ENVS="SpaceInvadersNoFrameskip-v4 QbertNoFrameskip-v4" | |
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 |