mirror of
https://github.com/vale981/ray
synced 2025-03-06 02:21:39 -05:00
72 lines
2 KiB
Python
72 lines
2 KiB
Python
import argparse
|
|
import os
|
|
|
|
import ray
|
|
from ray import tune
|
|
from ray.rllib.examples.env.mock_env import MockVectorEnv
|
|
from ray.rllib.utils.framework import try_import_tf, try_import_torch
|
|
from ray.rllib.utils.test_utils import check_learning_achieved
|
|
|
|
tf1, tf, tfv = try_import_tf()
|
|
torch, nn = try_import_torch()
|
|
|
|
parser = argparse.ArgumentParser()
|
|
parser.add_argument(
|
|
"--run",
|
|
type=str,
|
|
default="PPO",
|
|
help="The RLlib-registered algorithm to use.")
|
|
parser.add_argument(
|
|
"--framework",
|
|
choices=["tf", "tf2", "tfe", "torch"],
|
|
default="tf",
|
|
help="The DL framework specifier.")
|
|
parser.add_argument(
|
|
"--as-test",
|
|
action="store_true",
|
|
help="Whether this script should be run as a test: --stop-reward must "
|
|
"be achieved within --stop-timesteps AND --stop-iters.")
|
|
parser.add_argument(
|
|
"--stop-iters",
|
|
type=int,
|
|
default=50,
|
|
help="Number of iterations to train.")
|
|
parser.add_argument(
|
|
"--stop-timesteps",
|
|
type=int,
|
|
default=100000,
|
|
help="Number of timesteps to train.")
|
|
parser.add_argument(
|
|
"--stop-reward",
|
|
type=float,
|
|
default=35.0,
|
|
help="Reward at which we stop training.")
|
|
|
|
if __name__ == "__main__":
|
|
args = parser.parse_args()
|
|
ray.init()
|
|
|
|
# episode-len=100
|
|
# num-envs=4 (note that these are fake-envs as the MockVectorEnv only
|
|
# carries a single CartPole sub-env in it).
|
|
tune.register_env("custom_vec_env", lambda env_ctx: MockVectorEnv(100, 4))
|
|
|
|
config = {
|
|
"env": "custom_vec_env",
|
|
# Use GPUs iff `RLLIB_NUM_GPUS` env var set to > 0.
|
|
"num_gpus": int(os.environ.get("RLLIB_NUM_GPUS", "0")),
|
|
"num_workers": 2, # parallelism
|
|
"framework": args.framework,
|
|
}
|
|
|
|
stop = {
|
|
"training_iteration": args.stop_iters,
|
|
"timesteps_total": args.stop_timesteps,
|
|
"episode_reward_mean": args.stop_reward,
|
|
}
|
|
|
|
results = tune.run(args.run, config=config, stop=stop, verbose=1)
|
|
|
|
if args.as_test:
|
|
check_learning_achieved(results, args.stop_reward)
|
|
ray.shutdown()
|