ray/rllib/tests/test_external_multi_agent_env.py

68 lines
2.3 KiB
Python
Raw Normal View History

2019-04-07 04:58:14 +02:00
import gym
import numpy as np
import unittest
import ray
from ray.rllib.env.external_multi_agent_env import ExternalMultiAgentEnv
from ray.rllib.evaluation.rollout_worker import RolloutWorker
from ray.rllib.examples.env.multi_agent import BasicMultiAgent
from ray.rllib.tests.test_rollout_worker import MockPolicy
2019-04-07 04:58:14 +02:00
from ray.rllib.tests.test_external_env import make_simple_serving
SimpleMultiServing = make_simple_serving(True, ExternalMultiAgentEnv)
class TestExternalMultiAgentEnv(unittest.TestCase):
@classmethod
def setUpClass(cls) -> None:
ray.init(ignore_reinit_error=True)
@classmethod
def tearDownClass(cls) -> None:
ray.shutdown()
def test_external_multi_agent_env_complete_episodes(self):
2019-04-07 04:58:14 +02:00
agents = 4
ev = RolloutWorker(
2019-04-07 04:58:14 +02:00
env_creator=lambda _: SimpleMultiServing(BasicMultiAgent(agents)),
policy_spec=MockPolicy,
rollout_fragment_length=40,
2019-04-07 04:58:14 +02:00
batch_mode="complete_episodes")
for _ in range(3):
batch = ev.sample()
self.assertEqual(batch.count, 40)
self.assertEqual(len(np.unique(batch["agent_index"])), agents)
def test_external_multi_agent_env_truncate_episodes(self):
2019-04-07 04:58:14 +02:00
agents = 4
ev = RolloutWorker(
2019-04-07 04:58:14 +02:00
env_creator=lambda _: SimpleMultiServing(BasicMultiAgent(agents)),
policy_spec=MockPolicy,
rollout_fragment_length=40,
2019-04-07 04:58:14 +02:00
batch_mode="truncate_episodes")
for _ in range(3):
batch = ev.sample()
self.assertEqual(batch.count, 160)
self.assertEqual(len(np.unique(batch["agent_index"])), agents)
def test_external_multi_agent_env_sample(self):
2019-04-07 04:58:14 +02:00
agents = 2
act_space = gym.spaces.Discrete(2)
obs_space = gym.spaces.Discrete(2)
ev = RolloutWorker(
2019-04-07 04:58:14 +02:00
env_creator=lambda _: SimpleMultiServing(BasicMultiAgent(agents)),
policy_spec={
"p0": (MockPolicy, obs_space, act_space, {}),
"p1": (MockPolicy, obs_space, act_space, {}),
2019-04-07 04:58:14 +02:00
},
policy_mapping_fn=lambda agent_id: "p{}".format(agent_id % 2),
rollout_fragment_length=50)
2019-04-07 04:58:14 +02:00
batch = ev.sample()
self.assertEqual(batch.count, 50)
if __name__ == "__main__":
import pytest
import sys
sys.exit(pytest.main(["-v", __file__]))