import csv
import json
import time
import tempfile
import distutils
import subprocess
# --- 3rd party ---
import gym
import numpy as np
# --- my module ---
from unstable_baselines import logger
from unstable_baselines.lib import utils as ub_utils
LOG = logger.getLogger()
__all__ = [
'Monitor',
'MonitorToolChain',
'StatsRecorder',
'VideoRecorder',
]
# === Monitor ===
class Monitor(gym.Wrapper):
def __init__(self,
env: gym.Env,
root_dir: str = './monitor',
# --- my module ---
from unstable_baselines import logger
from unstable_baselines.base import (SavableModel,
TrainableModel)
from unstable_baselines.bugs import ReLU
from unstable_baselines.prob import MultiNormal
from unstable_baselines.utils import (normalize,
denormalize,
is_image_observation,
preprocess_observation,
get_input_tensor_from_space)
LOG = logger.getLogger('SD3')
# === Buffer ===
class ReplayBuffer():
'''
Replay buffer
'''
def __init__(self, buffer_size):
self.buffer_size = buffer_size
self.reset()
def reset(self):
self.pos = 0
self.full = False
env = WarpFrame(env)
env = FrameStack(env, 4)
return env
if __name__ == '__main__':
a = parse_args()
# === Reset logger ===
logger.Config.use(filename=a.logging,
level=a.log_level,
colored=True,
reset=True)
LOG = logger.getLogger('QRDQN')
# === Print welcome message ===
LOG.add_row('')
LOG.add_rows('QRDQN', fmt='{:@f:ANSI_Shadow}', align='center')
LOG.add_line()
LOG.add_rows('{}'.format(__copyright__))
LOG.flush('INFO')
time.sleep(1)
# === Print arguments ===
LOG.set_header('Arguments')
LOG.add_row('Log dir', a.logdir)
LOG.add_row('Logging path', a.logging)
LOG.add_row('Monitor path', a.monitor_dir)
LOG.add_row('Tensorboard path', a.tb_logdir)
import numpy as np
import tensorflow as tf
# --- my module ---
from unstable_baselines import logger
from unstable_baselines.lib.base import (SavableModel, TrainableModel)
from unstable_baselines.lib.patch import ReLU
from unstable_baselines.lib.prob import (Categorical, MultiNormal)
from unstable_baselines.lib.utils import (is_image_space,
preprocess_observation)
import unstable_baselines as ub
# create logger
LOG = logger.getLogger('PPO')
# === Buffers ===
"""
class GaeBuffer():
'''A Generalized Advantage Estimation Buffer'''
def __init__(self, gae_lambda=1.0, gamma=0.99):
'''GAE Buffer
refer to: https://arxiv.org/abs/1506.02438
Args:
gae_lambda (float, optional): Smoothing parameter. Defaults to 1.0.
gamma (float, optional): Discount factor. Defaults to 0.99.
'''
self.gae_lambda = gae_lambda
self.gamma = gamma
import numpy as np
import tensorflow as tf
# --- my module ---
from unstable_baselines import logger
from unstable_baselines.base import (SavableModel, TrainableModel)
from unstable_baselines.bugs import ReLU
from unstable_baselines.sche import Scheduler
from unstable_baselines.utils import (is_image_observation,
preprocess_observation,
get_input_tensor_from_space)
# create logger
LOG = logger.getLogger('IQN')
# === Buffers ===
class ReplayBuffer():
'''
Replay buffer
'''
def __init__(self, buffer_size):
self.buffer_size = buffer_size
self.reset()
def reset(self):
self.pos = 0
self.full = False
import numpy as np
import tensorflow as tf
# --- my module ---
from unstable_baselines import logger
from unstable_baselines.base import (SavableModel, TrainableModel)
from unstable_baselines.bugs import ReLU
from unstable_baselines.utils import (normalize, denormalize,
is_image_observation,
preprocess_observation,
get_input_tensor_from_space)
# create logger
LOG = logger.getLogger('TD3')
# === Buffer ===
class ReplayBuffer():
'''
Replay buffer
'''
def __init__(self, buffer_size):
self.buffer_size = buffer_size
self.reset()
def reset(self):
self.pos = 0
self.full = False
import numpy as np
import tensorflow as tf
# --- my module ---
from unstable_baselines import logger
from unstable_baselines.base import (SavableModel, TrainableModel)
from unstable_baselines.bugs import ReLU
from unstable_baselines.sche import Scheduler
from unstable_baselines.utils import (is_image_observation,
preprocess_observation,
get_input_tensor_from_space)
# create logger
LOG = logger.getLogger('C51')
def calc_bins(v_min, v_max, n_atoms):
'''Calculate canonical returns of each category
Args:
v_min (float): Minimum of value.
v_max (float): Maximum of value.
n_atoms (int): Number of categories.
Returns:
list: a list of canonical returns for each category
float: bin width
'''
delta_z = (v_max - v_min) / (n_atoms - 1)
