PPO playing CarRacing-v0 from https://github.com/sgoodfriend/rl-algo-impls/tree/e47a44c4d891f48885af0b1605b30d19fc67b5af
5b9b09f
| source benchmarks/train_loop.sh | |
| ALGOS="ppo" | |
| ENVS="SpaceInvadersNoFrameskip-v4 QbertNoFrameskip-v4" | |
| BENCHMARK_MAX_PROCS="${BENCHMARK_MAX_PROCS:-3}" | |
| train_loop $ALGOS "$ENVS" | xargs -I CMD -P $BENCHMARK_MAX_PROCS bash -c CMD |