PPO playing starpilot from https://github.com/sgoodfriend/rl-algo-impls/tree/227aa2fbde36e688a09d8ad309b0947721eef160
80e385e
| source benchmarks/train_loop.sh | |
| # export WANDB_PROJECT_NAME="rl-algo-impls" | |
| BENCHMARK_MAX_PROCS="${BENCHMARK_MAX_PROCS:-3}" | |
| ALGOS=( | |
| # "vpg" | |
| # "dqn" | |
| "ppo" | |
| ) | |
| ENVS=( | |
| "procgen-coinrun-easy" | |
| "procgen-starpilot-easy" | |
| "procgen-bossfight-easy" | |
| "procgen-bigfish-easy" | |
| ) | |
| train_loop "${ALGOS[*]}" "${ENVS[*]}" | xargs -I CMD -P $BENCHMARK_MAX_PROCS bash -c CMD | |