DQN playing LunarLander-v2 from https://github.com/sgoodfriend/rl-algo-impls/tree/2067e21d62fff5db60168687e7d9e89019a8bfc0
d643f40
ALGO="ppo" | |
ENVS="PongNoFrameskip-v4 BreakoutNoFrameskip-v4" | |
BENCHMARK_MAX_PROCS="${BENCHMARK_MAX_PROCS:-3}" | |
bash scripts/train_loop.sh -a $ALGO -e "$ENVS" | xargs -I CMD -P $BENCHMARK_MAX_PROCS bash -c CMD |