def main(args):
U.make_session(num_cpu=1).__enter__()
set_global_seeds(args.seed)
env = gym.make(args.env_id)
def policy_fn(name, ob_space, ac_space, reuse=False):
return mlp_policy.MlpPolicy(name=name, ob_space=ob_space, ac_space=ac_space,
reuse=reuse, hid_size=args.policy_hidden_size, num_hid_layers=2)
env = bench.Monitor(env, logger.get_dir() and
osp.join(logger.get_dir(), "monitor.json"))
env.seed(args.seed)
gym.logger.setLevel(logging.WARN)
task_name = get_task_name(args)
args.checkpoint_dir = osp.join(args.checkpoint_dir, task_name)
args.log_dir = osp.join(args.log_dir, task_name)
dataset = Mujoco_Dset(expert_path=args.expert_path, traj_limitation=args.traj_limitation)
savedir_fname = learn(env,
policy_fn,
dataset,
max_iters=args.BC_max_iter,
ckpt_dir=args.checkpoint_dir,
log_dir=args.log_dir,
task_name=task_name,
verbose=True)
avg_len, avg_ret = runner(env,
policy_fn,
savedir_fname,
timesteps_per_batch=1024,
number_trajs=10,
stochastic_policy=args.stochastic_policy,
save=args.save_sample,
reuse=True)
def make_robotics_env(env_id, seed, rank=0):
"""
Create a wrapped, monitored gym.Env for MuJoCo.
"""
set_global_seeds(seed)
env = gym.make(env_id)
env = FlattenDictWrapper(env, ['observation', 'desired_goal'])
env = Monitor(
env, logger.get_dir() and os.path.join(logger.get_dir(), str(rank)),
info_keywords=('is_success',))
env.seed(seed)
return env
def train(args, extra_args):
env_type, env_id = get_env_type(args)
print('env_type: {}'.format(env_type))
total_timesteps = int(args.num_timesteps)
seed = args.seed
learn = get_learn_function(args.alg)
alg_kwargs = get_learn_function_defaults(args.alg, env_type)
alg_kwargs.update(extra_args)
env = build_env(args)
if args.save_video_interval != 0:
env = VecVideoRecorder(
env,
osp.join(logger.get_dir(), "videos"),
record_video_trigger=lambda x: x % args.save_video_interval == 0,
video_length=args.save_video_length)
if args.network:
alg_kwargs['network'] = args.network
else:
if alg_kwargs.get('network') is None:
alg_kwargs['network'] = get_default_network(env_type)
print('Training {} on {}:{} with arguments \n{}'.format(
args.alg, env_type, env_id, alg_kwargs))
model = learn(env=env,
seed=seed,
total_timesteps=total_timesteps,
**alg_kwargs)
return model, env
def main():
logger.configure()
parser = mujoco_arg_parser()
parser.add_argument(
'--model-path', default=os.path.join(logger.get_dir(), 'humanoid_policy'))
parser.set_defaults(num_timesteps=int(5e7))
args = parser.parse_args()
if not args.play:
# train the model
train(num_timesteps=args.num_timesteps,
seed=args.seed, model_path=args.model_path)
else:
# construct the model object, load pre-trained model and render
pi = train(num_timesteps=1, seed=args.seed)
U.load_state(args.model_path)
env = make_mujoco_env('Humanoid-v2', seed=0)
ob = env.reset()
while True:
action = pi.act(stochastic=False, ob=ob)[0]
ob, _, done, _ = env.step(action)
env.render()
if done:
ob = env.reset()
def make_mujoco_env(env_id, seed, reward_scale=1.0):
"""
Create a wrapped, monitored gym.Env for MuJoCo.
"""
rank = MPI.COMM_WORLD.Get_rank()
myseed = seed + 1000 * rank if seed is not None else None
set_global_seeds(myseed)
env = gym.make(env_id)
logger_path = None if logger.get_dir() is None else os.path.join(
logger.get_dir(), str(rank))
env = Monitor(env, logger_path, allow_early_resets=True)
env.seed(seed)
if reward_scale != 1.0:
from deephyper.search.nas.baselines.common.retro_wrappers import RewardScaler
env = RewardScaler(env, reward_scale)
return env
def main():
logger.configure()
env = make_atari('PongNoFrameskip-v4')
env = bench.Monitor(env, logger.get_dir())
env = deepq.wrap_atari_dqn(env)
model = deepq.learn(
env,
"conv_only",
convs=[(32, 8, 4), (64, 4, 2), (64, 3, 1)],
hiddens=[256],
dueling=True,
lr=1e-4,
total_timesteps=int(1e7),
buffer_size=10000,
exploration_fraction=0.1,
exploration_final_eps=0.01,
train_freq=4,
learning_starts=10000,
target_network_update_freq=1000,
gamma=0.99,
)
model.save('pong_model.pkl')
env.close()
def make_vec_env(env_id, env_type, num_env, seed,
wrapper_kwargs=None,
start_index=0,
reward_scale=1.0,
flatten_dict_observations=True,
gamestate=None):
"""
Create a wrapped, monitored SubprocVecEnv for Atari and MuJoCo.
"""
wrapper_kwargs = wrapper_kwargs or {}
mpi_rank = MPI.COMM_WORLD.Get_rank() if MPI else 0
seed = seed + 10000 * mpi_rank if seed is not None else None
logger_dir = logger.get_dir()
def make_thunk(rank):
return lambda: make_env(
env_id=env_id,
env_type=env_type,
mpi_rank=mpi_rank,
subrank=rank,
seed=seed,
reward_scale=reward_scale,
gamestate=gamestate,
flatten_dict_observations=flatten_dict_observations,
wrapper_kwargs=wrapper_kwargs,
logger_dir=logger_dir
)
set_global_seeds(seed)
if num_env > 1:
return SubprocVecEnv([make_thunk(i + start_index) for i in range(num_env)])
else:
return DummyVecEnv([make_thunk(start_index)])
def main(args):
U.make_session(num_cpu=1).__enter__()
set_global_seeds(args.seed)
env = gym.make(args.env_id)
def policy_fn(name, ob_space, ac_space, reuse=False):
return mlp_policy.MlpPolicy(name=name,
ob_space=ob_space,
ac_space=ac_space,
reuse=reuse,
hid_size=args.policy_hidden_size,
num_hid_layers=2)
env = bench.Monitor(
env,
logger.get_dir() and osp.join(logger.get_dir(), "monitor.json"))
env.seed(args.seed)
gym.logger.setLevel(logging.WARN)
task_name = get_task_name(args)
args.checkpoint_dir = osp.join(args.checkpoint_dir, task_name)
args.log_dir = osp.join(args.log_dir, task_name)
if args.task == 'train':
dataset = Mujoco_Dset(expert_path=args.expert_path,
traj_limitation=args.traj_limitation)
reward_giver = TransitionClassifier(env,
args.adversary_hidden_size,
entcoeff=args.adversary_entcoeff)
train(env, args.seed, policy_fn, reward_giver, dataset, args.algo,
args.g_step, args.d_step, args.policy_entcoeff,
args.num_timesteps, args.save_per_iter, args.checkpoint_dir,
args.log_dir, args.pretrained, args.BC_max_iter, task_name)
elif args.task == 'evaluate':
runner(env,
policy_fn,
args.load_model_path,
timesteps_per_batch=1024,
number_trajs=10,
stochastic_policy=args.stochastic_policy,
save=args.save_sample)
else:
raise NotImplementedError
env.close()
def train(env_id, num_timesteps, seed):
from deephyper.search.nas.baselines.ppo1 import pposgd_simple, cnn_policy
import deephyper.search.nas.baselines.common.tf_util as U
rank = MPI.COMM_WORLD.Get_rank()
sess = U.single_threaded_session()
sess.__enter__()
if rank == 0:
logger.configure()
else:
logger.configure(format_strs=[])
workerseed = seed + 10000 * MPI.COMM_WORLD.Get_rank(
) if seed is not None else None
set_global_seeds(workerseed)
env = make_atari(env_id)
def policy_fn(name, ob_space, ac_space): # pylint: disable=W0613
return cnn_policy.CnnPolicy(name=name,
ob_space=ob_space,
ac_space=ac_space)
env = bench.Monitor(
env,
logger.get_dir() and osp.join(logger.get_dir(), str(rank)))
env.seed(workerseed)
env = wrap_deepmind(env)
env.seed(workerseed)
pposgd_simple.learn(env,
policy_fn,
max_timesteps=int(num_timesteps * 1.1),
timesteps_per_actorbatch=256,
clip_param=0.2,
entcoeff=0.01,
optim_epochs=4,
optim_stepsize=1e-3,
optim_batchsize=64,
gamma=0.99,
lam=0.95,
schedule='linear')
env.close()
def make_env(subrank=None):
env = gym.make(env_name)
if subrank is not None and logger.get_dir() is not None:
try:
from mpi4py import MPI
mpi_rank = MPI.COMM_WORLD.Get_rank()
except ImportError:
MPI = None
mpi_rank = 0
logger.warn(
'Running with a single MPI process. This should work, but the results may differ from the ones publshed in Plappert et al.'
)
max_episode_steps = env._max_episode_steps
env = Monitor(env,
os.path.join(logger.get_dir(),
str(mpi_rank) + '.' + str(subrank)),
allow_early_resets=True)
# hack to re-expose _max_episode_steps (ideally should replace reliance on it downstream)
env = gym.wrappers.TimeLimit(env,
max_episode_steps=max_episode_steps)
return env
def save_act(self, path=None):
"""Save model to a pickle located at `path`"""
if path is None:
path = os.path.join(logger.get_dir(), "model.pkl")
with tempfile.TemporaryDirectory() as td:
save_variables(os.path.join(td, "model"))
arc_name = os.path.join(td, "packed.zip")
with zipfile.ZipFile(arc_name, 'w') as zipf:
for root, dirs, files in os.walk(td):
for fname in files:
file_path = os.path.join(root, fname)
if file_path != arc_name:
zipf.write(file_path,
os.path.relpath(file_path, td))
with open(arc_name, "rb") as f:
model_data = f.read()
with open(path, "wb") as f:
cloudpickle.dump((model_data, self._act_params), f)
def learn(*,
network,
env,
total_timesteps,
eval_env=None,
seed=None,
nsteps=128,
ent_coef=0.0,
lr=3e-4,
vf_coef=0.5,
max_grad_norm=0.5,
gamma=0.99,
lam=0.95,
log_interval=10,
nminibatches=1,
noptepochs=4,
cliprange=0.2,
save_interval=10,
load_path=None,
model_fn=None,
**network_kwargs):
"""
Learn policy using PPO algorithm (https://arxiv.org/abs/1707.06347)
Parameters:
----------
network: policy network search_space. Either string (mlp, lstm, lnlstm, cnn_lstm, cnn, cnn_small, conv_only - see baselines.common/models.py for full list)
specifying the standard network search_space, or a function that takes tensorflow tensor as input and returns
tuple (output_tensor, extra_feed) where output tensor is the last network layer output, extra_feed is None for feed-forward
neural nets, and extra_feed is a dictionary describing how to feed state into the network for recurrent neural nets.
See common/models.py/lstm for more details on using recurrent nets in policies
env: baselines.common.vec_env.VecEnv environment. Needs to be vectorized for parallel environment simulation.
The environments produced by gym.make can be wrapped using baselines.common.vec_env.DummyVecEnv class.
nsteps: int number of steps of the vectorized environment per update (i.e. batch size is nsteps * nenv where
nenv is number of environment copies simulated in parallel)
total_timesteps: int number of timesteps (i.e. number of actions taken in the environment)
ent_coef: float policy entropy coefficient in the optimization objective
lr: float or function learning rate, constant or a schedule function [0,1] -> R+ where 1 is beginning of the
training and 0 is the end of the training.
vf_coef: float value function loss coefficient in the optimization objective
max_grad_norm: float or None gradient norm clipping coefficient
gamma: float discounting factor for rewards
lam: float advantage estimation discounting factor (lambda in the paper)
log_interval: int number of timesteps between logging events
nminibatches: int number of training minibatches per update. For recurrent policies,
should be smaller or equal than number of environments run in parallel.
noptepochs: int number of training epochs per update
cliprange: float or function clipping range, constant or schedule function [0,1] -> R+ where 1 is beginning of the training
and 0 is the end of the training
save_interval: int number of timesteps between saving events
load_path: str path to load the model from
**network_kwargs: keyword arguments to the policy / network builder. See baselines.common/policies.py/build_policy and arguments to a particular type of network
For instance, 'mlp' network search_space has arguments num_hidden and num_layers.
"""
set_global_seeds(seed)
if isinstance(lr, float):
lr = constfn(lr)
else:
assert callable(lr)
if isinstance(cliprange, float):
cliprange = constfn(cliprange)
else:
assert callable(cliprange)
#total_timesteps = int(total_timesteps)
policy = build_ppo_policy(env, network, **network_kwargs)
# Get the nb of env
nenvs = env.num_envs
# Get state_space and action_space
ob_space = env.observation_space
ac_space = env.action_space
# Calculate the batch_size
nbatch = nenvs * nsteps
nbatch_train = nbatch // nminibatches
# Instantiate the model object (that creates act_model and train_model)
if model_fn is None:
from deephyper.search.nas.baselines.ppo2.model import Model
model_fn = Model
model = model_fn(policy=policy,
ob_space=ob_space,
ac_space=ac_space,
nbatch_act=nenvs,
nbatch_train=nbatch_train,
nsteps=nsteps,
ent_coef=ent_coef,
vf_coef=vf_coef,
max_grad_norm=max_grad_norm)
if load_path is not None:
model.load(load_path)
allvars = tf.get_collection(tf.GraphKeys.GLOBAL_VARIABLES,
scope=model.name)
display_var_info(allvars)
# Instantiate the runner object
runner = Runner(env=env,
model=model,
nsteps=nsteps,
gamma=gamma,
ob_space=ob_space,
lam=lam)
if eval_env is not None:
eval_runner = Runner(env=eval_env,
model=model,
nsteps=nsteps,
gamma=gamma,
ob_space=ob_space,
lam=lam)
epinfobuf = deque(maxlen=100)
if eval_env is not None:
eval_epinfobuf = deque(maxlen=100)
# Start total timer
tfirststart = time.perf_counter()
nupdates = total_timesteps // nbatch
# for update in range(1, nupdates + 1):
update = 1
while True:
if not math.isnan(nupdates) and update >= nupdates:
break
assert nbatch % nminibatches == 0
# Start timer
tstart = time.perf_counter()
frac = 1.0 - (update - 1.0) / nupdates
# Calculate the learning rate
lrnow = lr(frac)
# Calculate the cliprange
cliprangenow = cliprange(frac)
# Get minibatch
minibatch = runner.run()
if eval_env is not None:
eval_minibatch = eval_runner.run()
_eval_obs = eval_minibatch['observations'] # noqa: F841
_eval_returns = eval_minibatch['returns'] # noqa: F841
_eval_masks = eval_minibatch['masks'] # noqa: F841
_eval_actions = eval_minibatch['actions'] # noqa: F841
_eval_values = eval_minibatch['values'] # noqa: F841
_eval_neglogpacs = eval_minibatch['neglogpacs'] # noqa: F841
_eval_states = eval_minibatch['state'] # noqa: F841
eval_epinfos = eval_minibatch['epinfos']
epinfobuf.extend(minibatch.pop('epinfos'))
if eval_env is not None:
eval_epinfobuf.extend(eval_epinfos)
# Here what we're going to do is for each minibatch calculate the loss and append it.
mblossvals = []
# Index of each element of batch_size
# Create the indices array
inds = np.arange(nbatch)
for _ in range(noptepochs):
# Randomize the indexes
np.random.shuffle(inds)
# 0 to batch_size with batch_train_size step
for start in range(0, nbatch, nbatch_train):
end = start + nbatch_train
mbinds = inds[start:end]
slices = {key: minibatch[key][mbinds] for key in minibatch}
mblossvals.append(model.train(lrnow, cliprangenow, **slices))
# Feedforward --> get losses --> update
lossvals = np.mean(mblossvals, axis=0)
# End timer
tnow = time.perf_counter()
# Calculate the fps (frame per second)
fps = int(nbatch / (tnow - tstart))
if update % log_interval == 0 or update == 1:
# Calculates if value function is a good predicator of the returns (ev > 1)
# or if it's just worse than predicting nothing (ev =< 0)
ev = explained_variance(minibatch['values'], minibatch['returns'])
logger.logkv("serial_timesteps", update * nsteps)
logger.logkv("nupdates", update)
logger.logkv("total_timesteps", update * nbatch)
logger.logkv("fps", fps)
logger.logkv("explained_variance", float(ev))
logger.logkv('eprewmean',
safemean([epinfo['r'] for epinfo in epinfobuf]))
logger.logkv('eplenmean',
safemean([epinfo['l'] for epinfo in epinfobuf]))
logger.logkv('rewards_per_step', safemean(minibatch['rewards']))
logger.logkv('advantages_per_step', safemean(minibatch['advs']))
if eval_env is not None:
logger.logkv(
'eval_eprewmean',
safemean([epinfo['r'] for epinfo in eval_epinfobuf]))
logger.logkv(
'eval_eplenmean',
safemean([epinfo['l'] for epinfo in eval_epinfobuf]))
logger.logkv('time_elapsed', tnow - tfirststart)
for (lossval, lossname) in zip(lossvals, model.loss_names):
logger.logkv(lossname, lossval)
if MPI is None or MPI.COMM_WORLD.Get_rank() == 0:
logger.dumpkvs()
if save_interval and (update % save_interval == 0
or update == 1) and logger.get_dir() and (
MPI is None
or MPI.COMM_WORLD.Get_rank() == 0):
checkdir = osp.join(logger.get_dir(), 'checkpoints')
os.makedirs(checkdir, exist_ok=True)
savepath = osp.join(checkdir, '%.5i' % update)
print('Saving to', savepath)
model.save(savepath)
del minibatch
update += 1
return model
def learn(network, env,
seed=None,
total_timesteps=None,
nb_epochs=None, # with default settings, perform 1M steps total
nb_epoch_cycles=20,
nb_rollout_steps=100,
reward_scale=1.0,
render=False,
render_eval=False,
noise_type='adaptive-param_0.2',
normalize_returns=False,
normalize_observations=True,
critic_l2_reg=1e-2,
actor_lr=1e-4,
critic_lr=1e-3,
popart=False,
gamma=0.99,
clip_norm=None,
nb_train_steps=50, # per epoch cycle and MPI worker,
nb_eval_steps=100,
batch_size=64, # per MPI worker
tau=0.01,
eval_env=None,
param_noise_adaption_interval=50,
**network_kwargs):
set_global_seeds(seed)
if total_timesteps is not None:
assert nb_epochs is None
nb_epochs = int(total_timesteps) // (nb_epoch_cycles * nb_rollout_steps)
else:
nb_epochs = 500
if MPI is not None:
rank = MPI.COMM_WORLD.Get_rank()
else:
rank = 0
nb_actions = env.action_space.shape[-1]
assert (np.abs(env.action_space.low) == env.action_space.high).all() # we assume symmetric actions.
memory = Memory(limit=int(1e6), action_shape=env.action_space.shape, observation_shape=env.observation_space.shape)
critic = Critic(network=network, **network_kwargs)
actor = Actor(nb_actions, network=network, **network_kwargs)
action_noise = None
param_noise = None
if noise_type is not None:
for current_noise_type in noise_type.split(','):
current_noise_type = current_noise_type.strip()
if current_noise_type == 'none':
pass
elif 'adaptive-param' in current_noise_type:
_, stddev = current_noise_type.split('_')
param_noise = AdaptiveParamNoiseSpec(initial_stddev=float(stddev), desired_action_stddev=float(stddev))
elif 'normal' in current_noise_type:
_, stddev = current_noise_type.split('_')
action_noise = NormalActionNoise(mu=np.zeros(nb_actions), sigma=float(stddev) * np.ones(nb_actions))
elif 'ou' in current_noise_type:
_, stddev = current_noise_type.split('_')
action_noise = OrnsteinUhlenbeckActionNoise(mu=np.zeros(nb_actions), sigma=float(stddev) * np.ones(nb_actions))
else:
raise RuntimeError('unknown noise type "{}"'.format(current_noise_type))
max_action = env.action_space.high
logger.info('scaling actions by {} before executing in env'.format(max_action))
agent = DDPG(actor, critic, memory, env.observation_space.shape, env.action_space.shape,
gamma=gamma, tau=tau, normalize_returns=normalize_returns, normalize_observations=normalize_observations,
batch_size=batch_size, action_noise=action_noise, param_noise=param_noise, critic_l2_reg=critic_l2_reg,
actor_lr=actor_lr, critic_lr=critic_lr, enable_popart=popart, clip_norm=clip_norm,
reward_scale=reward_scale)
logger.info('Using agent with the following configuration:')
logger.info(str(agent.__dict__.items()))
eval_episode_rewards_history = deque(maxlen=100)
episode_rewards_history = deque(maxlen=100)
sess = U.get_session()
# Prepare everything.
agent.initialize(sess)
sess.graph.finalize()
agent.reset()
obs = env.reset()
if eval_env is not None:
eval_obs = eval_env.reset()
nenvs = obs.shape[0]
episode_reward = np.zeros(nenvs, dtype = np.float32) #vector
episode_step = np.zeros(nenvs, dtype = int) # vector
episodes = 0 #scalar
t = 0 # scalar
epoch = 0
start_time = time.time()
epoch_episode_rewards = []
epoch_episode_steps = []
epoch_actions = []
epoch_qs = []
epoch_episodes = 0
for epoch in range(nb_epochs):
for cycle in range(nb_epoch_cycles):
# Perform rollouts.
if nenvs > 1:
# if simulating multiple envs in parallel, impossible to reset agent at the end of the episode in each
# of the environments, so resetting here instead
agent.reset()
for t_rollout in range(nb_rollout_steps):
# Predict next action.
action, q, _, _ = agent.step(obs, apply_noise=True, compute_Q=True)
# Execute next action.
if rank == 0 and render:
env.render()
# max_action is of dimension A, whereas action is dimension (nenvs, A) - the multiplication gets broadcasted to the batch
new_obs, r, done, info = env.step(max_action * action) # scale for execution in env (as far as DDPG is concerned, every action is in [-1, 1])
# note these outputs are batched from vecenv
t += 1
if rank == 0 and render:
env.render()
episode_reward += r
episode_step += 1
# Book-keeping.
epoch_actions.append(action)
epoch_qs.append(q)
agent.store_transition(obs, action, r, new_obs, done) #the batched data will be unrolled in memory.py's append.
obs = new_obs
for d in range(len(done)):
if done[d]:
# Episode done.
epoch_episode_rewards.append(episode_reward[d])
episode_rewards_history.append(episode_reward[d])
epoch_episode_steps.append(episode_step[d])
episode_reward[d] = 0.
episode_step[d] = 0
epoch_episodes += 1
episodes += 1
if nenvs == 1:
agent.reset()
# Train.
epoch_actor_losses = []
epoch_critic_losses = []
epoch_adaptive_distances = []
for t_train in range(nb_train_steps):
# Adapt param noise, if necessary.
if memory.nb_entries >= batch_size and t_train % param_noise_adaption_interval == 0:
distance = agent.adapt_param_noise()
epoch_adaptive_distances.append(distance)
cl, al = agent.train()
epoch_critic_losses.append(cl)
epoch_actor_losses.append(al)
agent.update_target_net()
# Evaluate.
eval_episode_rewards = []
eval_qs = []
if eval_env is not None:
nenvs_eval = eval_obs.shape[0]
eval_episode_reward = np.zeros(nenvs_eval, dtype = np.float32)
for t_rollout in range(nb_eval_steps):
eval_action, eval_q, _, _ = agent.step(eval_obs, apply_noise=False, compute_Q=True)
eval_obs, eval_r, eval_done, eval_info = eval_env.step(max_action * eval_action) # scale for execution in env (as far as DDPG is concerned, every action is in [-1, 1])
if render_eval:
eval_env.render()
eval_episode_reward += eval_r
eval_qs.append(eval_q)
for d in range(len(eval_done)):
if eval_done[d]:
eval_episode_rewards.append(eval_episode_reward[d])
eval_episode_rewards_history.append(eval_episode_reward[d])
eval_episode_reward[d] = 0.0
if MPI is not None:
mpi_size = MPI.COMM_WORLD.Get_size()
else:
mpi_size = 1
# Log stats.
# XXX shouldn't call np.mean on variable length lists
duration = time.time() - start_time
stats = agent.get_stats()
combined_stats = stats.copy()
combined_stats['rollout/return'] = np.mean(epoch_episode_rewards)
combined_stats['rollout/return_history'] = np.mean(episode_rewards_history)
combined_stats['rollout/episode_steps'] = np.mean(epoch_episode_steps)
combined_stats['rollout/actions_mean'] = np.mean(epoch_actions)
combined_stats['rollout/Q_mean'] = np.mean(epoch_qs)
combined_stats['train/loss_actor'] = np.mean(epoch_actor_losses)
combined_stats['train/loss_critic'] = np.mean(epoch_critic_losses)
combined_stats['train/param_noise_distance'] = np.mean(epoch_adaptive_distances)
combined_stats['total/duration'] = duration
combined_stats['total/steps_per_second'] = float(t) / float(duration)
combined_stats['total/episodes'] = episodes
combined_stats['rollout/episodes'] = epoch_episodes
combined_stats['rollout/actions_std'] = np.std(epoch_actions)
# Evaluation statistics.
if eval_env is not None:
combined_stats['eval/return'] = eval_episode_rewards
combined_stats['eval/return_history'] = np.mean(eval_episode_rewards_history)
combined_stats['eval/Q'] = eval_qs
combined_stats['eval/episodes'] = len(eval_episode_rewards)
def as_scalar(x):
if isinstance(x, np.ndarray):
assert x.size == 1
return x[0]
elif np.isscalar(x):
return x
else:
raise ValueError('expected scalar, got %s'%x)
combined_stats_sums = np.array([ np.array(x).flatten()[0] for x in combined_stats.values()])
if MPI is not None:
combined_stats_sums = MPI.COMM_WORLD.allreduce(combined_stats_sums)
combined_stats = {k : v / mpi_size for (k,v) in zip(combined_stats.keys(), combined_stats_sums)}
# Total statistics.
combined_stats['total/epochs'] = epoch + 1
combined_stats['total/steps'] = t
for key in sorted(combined_stats.keys()):
logger.record_tabular(key, combined_stats[key])
if rank == 0:
logger.dump_tabular()
logger.info('')
logdir = logger.get_dir()
if rank == 0 and logdir:
if hasattr(env, 'get_state'):
with open(os.path.join(logdir, 'env_state.pkl'), 'wb') as f:
pickle.dump(env.get_state(), f)
if eval_env and hasattr(eval_env, 'get_state'):
with open(os.path.join(logdir, 'eval_env_state.pkl'), 'wb') as f:
pickle.dump(eval_env.get_state(), f)
return agent
def learn(network,
env,
seed,
total_timesteps=int(40e6),
gamma=0.99,
log_interval=1,
nprocs=32,
nsteps=20,
ent_coef=0.01,
vf_coef=0.5,
vf_fisher_coef=1.0,
lr=0.25,
max_grad_norm=0.5,
kfac_clip=0.001,
save_interval=None,
lrschedule='linear',
load_path=None,
is_async=True,
**network_kwargs):
set_global_seeds(seed)
if network == 'cnn':
network_kwargs['one_dim_bias'] = True
policy = build_policy(env, network, **network_kwargs)
nenvs = env.num_envs
ob_space = env.observation_space
ac_space = env.action_space
make_model = lambda: Model(policy,
ob_space,
ac_space,
nenvs,
total_timesteps,
nprocs=nprocs,
nsteps=nsteps,
ent_coef=ent_coef,
vf_coef=vf_coef,
vf_fisher_coef=vf_fisher_coef,
lr=lr,
max_grad_norm=max_grad_norm,
kfac_clip=kfac_clip,
lrschedule=lrschedule,
is_async=is_async)
if save_interval and logger.get_dir():
import cloudpickle
with open(osp.join(logger.get_dir(), 'make_model.pkl'), 'wb') as fh:
fh.write(cloudpickle.dumps(make_model))
model = make_model()
if load_path is not None:
model.load(load_path)
runner = Runner(env, model, nsteps=nsteps, gamma=gamma)
epinfobuf = deque(maxlen=100)
nbatch = nenvs * nsteps
tstart = time.time()
coord = tf.train.Coordinator()
if is_async:
enqueue_threads = model.q_runner.create_threads(model.sess,
coord=coord,
start=True)
else:
enqueue_threads = []
for update in range(1, total_timesteps // nbatch + 1):
obs, states, rewards, masks, actions, values, epinfos = runner.run()
epinfobuf.extend(epinfos)
policy_loss, value_loss, policy_entropy = model.train(
obs, states, rewards, masks, actions, values)
model.old_obs = obs
nseconds = time.time() - tstart
fps = int((update * nbatch) / nseconds)
if update % log_interval == 0 or update == 1:
ev = explained_variance(values, rewards)
logger.record_tabular("nupdates", update)
logger.record_tabular("total_timesteps", update * nbatch)
logger.record_tabular("fps", fps)
logger.record_tabular("policy_entropy", float(policy_entropy))
logger.record_tabular("policy_loss", float(policy_loss))
logger.record_tabular("value_loss", float(value_loss))
logger.record_tabular("explained_variance", float(ev))
logger.record_tabular(
"eprewmean", safemean([epinfo['r'] for epinfo in epinfobuf]))
logger.record_tabular(
"eplenmean", safemean([epinfo['l'] for epinfo in epinfobuf]))
logger.dump_tabular()
if save_interval and (update % save_interval == 0
or update == 1) and logger.get_dir():
savepath = osp.join(logger.get_dir(), 'checkpoint%.5i' % update)
print('Saving to', savepath)
model.save(savepath)
coord.request_stop()
coord.join(enqueue_threads)
return model
def learn(*, network, env, total_timesteps,
seed=None,
eval_env=None,
replay_strategy='future',
policy_save_interval=5,
clip_return=True,
demo_file=None,
override_params=None,
load_path=None,
save_path=None,
**kwargs
):
override_params = override_params or {}
if MPI is not None:
rank = MPI.COMM_WORLD.Get_rank()
num_cpu = MPI.COMM_WORLD.Get_size()
# Seed everything.
rank_seed = seed + 1000000 * rank if seed is not None else None
set_global_seeds(rank_seed)
# Prepare params.
params = config.DEFAULT_PARAMS
env_name = env.spec.id
params['env_name'] = env_name
params['replay_strategy'] = replay_strategy
if env_name in config.DEFAULT_ENV_PARAMS:
params.update(config.DEFAULT_ENV_PARAMS[env_name]) # merge env-specific parameters in
params.update(**override_params) # makes it possible to override any parameter
with open(os.path.join(logger.get_dir(), 'params.json'), 'w') as f:
json.dump(params, f)
params = config.prepare_params(params)
params['rollout_batch_size'] = env.num_envs
if demo_file is not None:
params['bc_loss'] = 1
params.update(kwargs)
config.log_params(params, logger=logger)
if num_cpu == 1:
logger.warn()
logger.warn('*** Warning ***')
logger.warn(
'You are running HER with just a single MPI worker. This will work, but the ' +
'experiments that we report in Plappert et al. (2018, https://arxiv.org/abs/1802.09464) ' +
'were obtained with --num_cpu 19. This makes a significant difference and if you ' +
'are looking to reproduce those results, be aware of this. Please also refer to ' +
'https://github.com/openai/baselines/issues/314 for further details.')
logger.warn('****************')
logger.warn()
dims = config.configure_dims(params)
policy = config.configure_ddpg(dims=dims, params=params, clip_return=clip_return)
if load_path is not None:
tf_util.load_variables(load_path)
rollout_params = {
'exploit': False,
'use_target_net': False,
'use_demo_states': True,
'compute_Q': False,
'T': params['T'],
}
eval_params = {
'exploit': True,
'use_target_net': params['test_with_polyak'],
'use_demo_states': False,
'compute_Q': True,
'T': params['T'],
}
for name in ['T', 'rollout_batch_size', 'gamma', 'noise_eps', 'random_eps']:
rollout_params[name] = params[name]
eval_params[name] = params[name]
eval_env = eval_env or env
rollout_worker = RolloutWorker(env, policy, dims, logger, monitor=True, **rollout_params)
evaluator = RolloutWorker(eval_env, policy, dims, logger, **eval_params)
n_cycles = params['n_cycles']
n_epochs = total_timesteps // n_cycles // rollout_worker.T // rollout_worker.rollout_batch_size
return train(
save_path=save_path, policy=policy, rollout_worker=rollout_worker,
evaluator=evaluator, n_epochs=n_epochs, n_test_rollouts=params['n_test_rollouts'],
n_cycles=params['n_cycles'], n_batches=params['n_batches'],
policy_save_interval=policy_save_interval, demo_file=demo_file)
