PPO playing MicrortsDefeatCoacAIShaped-v3 from https://github.com/sgoodfriend/rl-algo-impls/tree/4706d8dbb99b38e70d080c3de68d0751ea585a2f
7058eb5
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 |