DQN playing SpaceInvadersNoFrameskip-v4 from https://github.com/sgoodfriend/rl-algo-impls/tree/e8bc541d8b5e67bb4d3f2075282463fb61f5f2c6
6462893
| source benchmarks/train_loop.sh | |
| # export WANDB_PROJECT_NAME="rl-algo-impls" | |
| BENCHMARK_MAX_PROCS="${BENCHMARK_MAX_PROCS:-3}" | |
| ALGOS=( | |
| # "vpg" | |
| # "dqn" | |
| "ppo" | |
| ) | |
| ENVS=( | |
| "procgen-starpilot-hard" | |
| "procgen-starpilot-hard-2xIMPALA" | |
| "procgen-starpilot-hard-2xIMPALA-fat" | |
| "procgen-starpilot-hard-4xIMPALA" | |
| ) | |
| train_loop "${ALGOS[*]}" "${ENVS[*]}" | xargs -I CMD -P $BENCHMARK_MAX_PROCS bash -c CMD | |