ppo-QbertNoFrameskip-v4 / benchmarks /colab_carracing.sh
sgoodfriend's picture
PPO playing QbertNoFrameskip-v4 from https://github.com/sgoodfriend/rl-algo-impls/tree/5598ebc4b03054f16eebe76792486ba7bcacfc5c
e1cedec
raw
history blame
188 Bytes
source benchmarks/train_loop.sh
ALGOS="ppo"
ENVS="CarRacing-v0"
BENCHMARK_MAX_PROCS="${BENCHMARK_MAX_PROCS:-3}"
train_loop $ALGOS "$ENVS" | xargs -I CMD -P $BENCHMARK_MAX_PROCS bash -c CMD