def main(args):
U.make_session(num_cpu=1).__enter__()
set_global_seeds(args.seed)
print('Evaluating {}'.format(args.env))
bc_log = evaluate_env(args.env, args.seed, args.policy_hidden_size,
args.stochastic_policy, False, 'BC')
print('Evaluation for {}'.format(args.env))
print(bc_log)
gail_log = evaluate_env(args.env, args.seed, args.policy_hidden_size,
args.stochastic_policy, True, 'gail')
print('Evaluation for {}'.format(args.env))
print(gail_log)
plot(args.env, bc_log, gail_log, args.stochastic_policy)
def train(env_id, num_timesteps, seed):
from test.baselines.ppo1 import mlp_policy, pposgd_simple
sess = U.make_session(num_cpu=1)
sess.__enter__()
def policy_fn(name, ob_space, ac_space):
return mlp_policy.MlpPolicy(name=name,
ob_space=ob_space,
ac_space=ac_space,
hid_size=64,
num_hid_layers=2)
env = make_mujoco_env(env_id, seed)
pposgd_simple.learn(
env,
policy_fn,
max_timesteps=num_timesteps,
timesteps_per_actorbatch=5000,
clip_param=0.2,
entcoeff=0.0,
optim_epochs=10,
optim_stepsize=3e-4,
optim_batchsize=4048,
gamma=0.99,
lam=0.95,
schedule='linear',
)
env.close()
writer = tf.summary.FileWriter('dir/log', sess.graph) # write to file
merge_op = tf.summary.merge_all() # operation to merge all summary
Saver = tf.train.Saver(max_to_keep=10)
Saver.save(sess,
os.path.join(dir, 'trained_variables.ckpt'),
write_meta_graph=False)
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 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 __init__(self,
policy,
ob_space,
ac_space,
nenvs,
nsteps,
ent_coef=0.01,
vf_coef=0.5,
max_grad_norm=0.5,
lr=7e-4,
alpha=0.99,
epsilon=1e-5,
total_timesteps=int(80e6),
lrschedule='linear'):
sess = tf_util.make_session()
nbatch = nenvs * nsteps
A = tf.placeholder(tf.int32, [nbatch])
ADV = tf.placeholder(tf.float32, [nbatch])
R = tf.placeholder(tf.float32, [nbatch])
LR = tf.placeholder(tf.float32, [])
step_model = policy(sess, ob_space, ac_space, nenvs, 1, reuse=False)
train_model = policy(sess,
ob_space,
ac_space,
nenvs * nsteps,
nsteps,
reuse=True)
neglogpac = tf.nn.sparse_softmax_cross_entropy_with_logits(
logits=train_model.pi, labels=A)
pg_loss = tf.reduce_mean(ADV * neglogpac)
vf_loss = tf.reduce_mean(mse(tf.squeeze(train_model.vf), R))
entropy = tf.reduce_mean(cat_entropy(train_model.pi))
loss = pg_loss - entropy * ent_coef + vf_loss * vf_coef
params = find_trainable_variables("model")
grads = tf.gradients(loss, params)
if max_grad_norm is not None:
grads, grad_norm = tf.clip_by_global_norm(grads, max_grad_norm)
grads = list(zip(grads, params))
trainer = tf.train.RMSPropOptimizer(learning_rate=LR,
decay=alpha,
epsilon=epsilon)
_train = trainer.apply_gradients(grads)
lr = Scheduler(v=lr, nvalues=total_timesteps, schedule=lrschedule)
def train(obs, states, rewards, masks, actions, values):
advs = rewards - values
for step in range(len(obs)):
cur_lr = lr.value()
td_map = {
train_model.X: obs,
A: actions,
ADV: advs,
R: rewards,
LR: cur_lr
}
if states is not None:
td_map[train_model.S] = states
td_map[train_model.M] = masks
policy_loss, value_loss, policy_entropy, _ = sess.run(
[pg_loss, vf_loss, entropy, _train], td_map)
return policy_loss, value_loss, policy_entropy
def save(save_path):
ps = sess.run(params)
make_path(osp.dirname(save_path))
joblib.dump(ps, save_path)
def load(load_path):
loaded_params = joblib.load(load_path)
restores = []
for p, loaded_p in zip(params, loaded_params):
restores.append(p.assign(loaded_p))
sess.run(restores)
self.train = train
self.train_model = train_model
self.step_model = step_model
self.step = step_model.step
self.value = step_model.value
self.initial_state = step_model.initial_state
self.save = save
self.load = load
tf.global_variables_initializer().run(session=sess)
from test.baselines.deepq.replay_buffer import ReplayBuffer
from test.baselines.deepq.utils import BatchInput
from test.baselines.common.schedules import LinearSchedule
def model(inpt, num_actions, scope, reuse=False):
"""This model takes as input an observation and returns values of all actions."""
with tf.variable_scope(scope, reuse=reuse):
out = inpt
out = layers.fully_connected(out, num_outputs=64, activation_fn=tf.nn.tanh)
out = layers.fully_connected(out, num_outputs=num_actions, activation_fn=None)
return out
if __name__ == '__main__':
with U.make_session(8):
# Create the environment
env = gym.make("CartPole-v0")
# Create all the functions necessary to train the model
act, train, update_target, debug = deepq.build_train(
make_obs_ph=lambda name: BatchInput(env.observation_space.shape, name=name),
q_func=model,
num_actions=env.action_space.n,
optimizer=tf.train.AdamOptimizer(learning_rate=5e-4),
)
# Create the replay buffer
replay_buffer = ReplayBuffer(50000)
# Create the schedule for exploration starting from 1 (every action is random) down to
# 0.02 (98% of actions are selected according to values predicted by the model).
exploration = LinearSchedule(schedule_timesteps=10000, initial_p=1.0, final_p=0.02)