Secure your code as it's written. Use Snyk Code to scan source code in minutes - no build needed - and fix issues immediately.
prioritized_replay_beta0, prioritized_replay_beta_iters,
prioritized_replay_eps, experiment_name, load_path, network_kwargs):
env = DotaEnvironment()
sess = get_session()
set_global_seeds(seed)
q_func = build_q_func(network, **network_kwargs)
# capture the shape outside the closure so that the env object is not serialized
# by cloudpickle when serializing make_obs_ph
observation_space = env.observation_space
def make_obs_ph(name):
return ObservationInput(observation_space, name=name)
act, _, _, debug = deepq.build_train(
scope='deepq_act',
make_obs_ph=make_obs_ph,
q_func=q_func,
num_actions=env.action_space.n,
optimizer=tf.train.AdamOptimizer(learning_rate=lr),
gamma=gamma,
grad_norm_clipping=10, )
act_params = {
'make_obs_ph': make_obs_ph,
'q_func': q_func,
'num_actions': env.action_space.n, }
act = ActWrapper(act, act_params)
exploration = LinearSchedule(schedule_timesteps=int(exploration_fraction * total_timesteps),