import numpy as np
from deer.agent import NeuralAgent
from deer.q_networks.q_net_theano import MyQNetwork
from Toy_env import MyEnv as Toy_env
import deer.experiment.base_controllers as bc
if __name__ == "__main__":
rng = np.random.RandomState(123456)
# --- Instantiate environment ---
env = Toy_env(rng)
# --- Instantiate qnetwork ---
qnetwork = MyQNetwork(environment=env, random_state=rng)
# --- Instantiate agent ---
agent = NeuralAgent(env, qnetwork, random_state=rng)
# --- Bind controllers to the agent ---
# Before every training epoch, we want to print a summary of the agent's epsilon, discount and
# learning rate as well as the training epoch number.
agent.attach(bc.VerboseController())
# During training epochs, we want to train the agent after every action it takes.
# Plus, we also want to display after each training episode (!= than after every training) the average bellman
# residual and the average of the V values obtained during the last episode.
agent.attach(bc.TrainerController())
# All previous controllers control the agent during the epochs it goes through. However, we want to interleave a
if __name__ == "__main__":
logging.basicConfig(level=logging.INFO)
# --- Parse parameters ---
parameters = process_args(sys.argv[1:], Defaults)
if parameters.deterministic:
rng = np.random.RandomState(123456)
else:
rng = np.random.RandomState()
# --- Instantiate environment ---
env = MG_two_storages_env(rng)
# --- Instantiate qnetwork ---
qnetwork = MyQNetwork(env, parameters.rms_decay, parameters.rms_epsilon,
parameters.momentum, parameters.clip_delta,
parameters.freeze_interval, parameters.batch_size,
parameters.update_rule, rng)
# --- Instantiate agent ---
agent = NeuralAgent(
env, qnetwork, parameters.replay_memory_size,
max(env.inputDimensions()[i][0]
for i in range(len(env.inputDimensions()))), parameters.batch_size,
rng)
# --- Create unique filename for FindBestController ---
h = hash(vars(parameters), hash_name="sha1")
fname = "MG2S_" + h
print("The parameters hash is: {}".format(h))
print("The parameters are: {}".format(parameters))
parameters = process_args(sys.argv[1:], Defaults)
if parameters.deterministic:
rng = np.random.RandomState(12345)
else:
rng = np.random.RandomState()
# --- Instantiate environment ---
env = pendulum_env(rng)
# --- Instantiate qnetwork ---
qnetwork = MyQNetwork(env,
parameters.rms_decay,
parameters.rms_epsilon,
parameters.momentum,
parameters.clip_delta,
parameters.freeze_interval,
parameters.batch_size,
parameters.network_type,
parameters.update_rule,
parameters.batch_accumulator,
rng,
DoubleQ=True)
# --- Instantiate agent ---
agent = NeuralAgent(
env, qnetwork, parameters.replay_memory_size,
max(env.inputDimensions()[i][0]
for i in range(len(env.inputDimensions()))), parameters.batch_size,
rng)
# --- Bind controllers to the agent ---
# For comments, please refer to run_toy_env.py