#!/usr/bin/env python
import argparse
import json
import os
import random
import numpy as np
import ray
from ray.tune import Trainable, run, sample_from
from ray.tune.schedulers import AsyncHyperBandScheduler
class MyTrainableClass(Trainable):
"""Example agent whose learning curve is a random sigmoid.
The dummy hyperparameters "width" and "height" determine the slope and
maximum reward value reached.
"""
def setup(self, config):
self.timestep = 0
def step(self):
self.timestep += 1
v = np.tanh(float(self.timestep) / self.config.get("width", 1))
v *= self.config.get("height", 1)
# Here we use `episode_reward_mean`, but you can also report other
# objectives such as loss or accuracy.
return {"episode_reward_mean": v}
def save_checkpoint(self, checkpoint_dir):
path = os.path.join(checkpoint_dir, "checkpoint")
with open(path, "w") as f:
f.write(json.dumps({"timestep": self.timestep}))
return path
def load_checkpoint(self, checkpoint_path):
with open(checkpoint_path) as f:
self.timestep = json.loads(f.read())["timestep"]
if __name__ == "__main__":
parser = argparse.ArgumentParser()
parser.add_argument(
"--smoke-test", action="store_true", help="Finish quickly for testing")
parser.add_argument(
"--ray-address",
help="Address of Ray cluster for seamless distributed execution.")
args, _ = parser.parse_known_args()
ray.init(address=args.ray_address)
# asynchronous hyperband early stopping, configured with
# `episode_reward_mean` as the
# objective and `training_iteration` as the time unit,
# which is automatically filled by Tune.
ahb = AsyncHyperBandScheduler(
time_attr="training_iteration",
metric="episode_reward_mean",
mode="max",
grace_period=5,
max_t=100)
run(MyTrainableClass,
name="asynchyperband_test",
scheduler=ahb,
stop={"training_iteration": 1 if args.smoke_test else 99999},
num_samples=20,
resources_per_trial={
"cpu": 1,
"gpu": 0
},
config={
"width": sample_from(lambda spec: 10 + int(90 * random.random())),
"height": sample_from(lambda spec: int(100 * random.random())),
})