mirror of
https://github.com/vale981/ray
synced 2025-03-06 10:31:39 -05:00
57544b1ff9
- This PR completes any previously missing PyTorch Model counterparts to TFModels in examples/models. - It also makes sure, all example scripts in the rllib/examples folder are tested for both frameworks and learn the given task (this is often currently not checked) using a --as-test flag in connection with a --stop-reward.
62 lines
2 KiB
Python
62 lines
2 KiB
Python
"""Example of using a custom RNN keras model."""
|
|
|
|
import argparse
|
|
|
|
import ray
|
|
from ray import tune
|
|
from ray.tune.registry import register_env
|
|
from ray.rllib.examples.env.repeat_after_me_env import RepeatAfterMeEnv
|
|
from ray.rllib.examples.env.repeat_initial_obs_env import RepeatInitialObsEnv
|
|
from ray.rllib.examples.models.rnn_model import RNNModel, TorchRNNModel
|
|
from ray.rllib.models import ModelCatalog
|
|
from ray.rllib.utils.test_utils import check_learning_achieved
|
|
|
|
parser = argparse.ArgumentParser()
|
|
parser.add_argument("--run", type=str, default="PPO")
|
|
parser.add_argument("--env", type=str, default="RepeatAfterMeEnv")
|
|
parser.add_argument("--num-cpus", type=int, default=0)
|
|
parser.add_argument("--as-test", action="store_true")
|
|
parser.add_argument("--torch", action="store_true")
|
|
parser.add_argument("--stop-reward", type=float, default=90)
|
|
parser.add_argument("--stop-iters", type=int, default=100)
|
|
parser.add_argument("--stop-timesteps", type=int, default=100000)
|
|
|
|
if __name__ == "__main__":
|
|
args = parser.parse_args()
|
|
|
|
ray.init(num_cpus=args.num_cpus or None)
|
|
|
|
ModelCatalog.register_custom_model(
|
|
"rnn", TorchRNNModel if args.torch else RNNModel)
|
|
register_env("RepeatAfterMeEnv", lambda c: RepeatAfterMeEnv(c))
|
|
register_env("RepeatInitialObsEnv", lambda _: RepeatInitialObsEnv())
|
|
|
|
config = {
|
|
"env": args.env,
|
|
"env_config": {
|
|
"repeat_delay": 2,
|
|
},
|
|
"gamma": 0.9,
|
|
"num_workers": 0,
|
|
"num_envs_per_worker": 20,
|
|
"entropy_coeff": 0.001,
|
|
"num_sgd_iter": 5,
|
|
"vf_loss_coeff": 1e-5,
|
|
"model": {
|
|
"custom_model": "rnn",
|
|
"max_seq_len": 20,
|
|
},
|
|
"use_pytorch": args.torch,
|
|
}
|
|
|
|
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)
|
|
|
|
if args.as_test:
|
|
check_learning_achieved(results, args.stop_reward)
|
|
ray.shutdown()
|