PPO playing MicrortsDefeatRandomEnemySparseReward-v3 from https://github.com/sgoodfriend/rl-algo-impls/tree/388c8ed9f7db1d5f5c380d981aeb8a85f34eeacb
9fd539b
| ALGO="ppo" | |
| ENVS="CarRacing-v0" | |
| 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 |