PPO playing procgen-bigfish-easy from https://github.com/sgoodfriend/rl-algo-impls/tree/21ee1ab96a186676e5ed2f8c3185902f7c7bca7a
a678795
| source benchmarks/train_loop.sh | |
| ALGOS="ppo" | |
| ENVS="PongNoFrameskip-v4 BreakoutNoFrameskip-v4" | |
| BENCHMARK_MAX_PROCS="${BENCHMARK_MAX_PROCS:-3}" | |
| train_loop $ALGOS "$ENVS" | xargs -I CMD -P $BENCHMARK_MAX_PROCS bash -c CMD |