PPO playing LunarLander-v2 from https://github.com/sgoodfriend/rl-algo-impls/tree/5598ebc4b03054f16eebe76792486ba7bcacfc5c
250f951
| 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 |