sgoodfriend's picture
PPO playing MicrortsRandomEnemyShapedReward3-v1 from https://github.com/sgoodfriend/rl-algo-impls/tree/fb34ab86707f5e2db85e821ff7dbdc624072d640
5c3cdcb
raw
history blame contribute delete
205 Bytes
ALGO="ppo"
ENVS="PongNoFrameskip-v4 BreakoutNoFrameskip-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