def test_piecewise_schedule():
ps = PiecewiseSchedule([(-5, 100), (5, 200), (10, 50), (100, 50),
(200, -50)],
outside_value=500)
assert np.isclose(ps.value(-10), 500)
assert np.isclose(ps.value(0), 150)
assert np.isclose(ps.value(5), 200)
assert np.isclose(ps.value(9), 80)
assert np.isclose(ps.value(50), 50)
assert np.isclose(ps.value(80), 50)
assert np.isclose(ps.value(150), 0)
assert np.isclose(ps.value(175), -25)
assert np.isclose(ps.value(201), 500)
assert np.isclose(ps.value(500), 500)
assert np.isclose(ps.value(200 - 1e-10), -50)
# Create training graph and replay buffer
act, train, update_target, debug, craft_adv = deepq.build_train(
make_obs_ph=lambda name: U.Uint8Input(env.observation_space.shape,
name=name),
q_func=dueling_model if args.dueling else model,
num_actions=env.action_space.n,
optimizer=tf.train.AdamOptimizer(learning_rate=args.lr,
epsilon=1e-4),
gamma=0.99,
grad_norm_clipping=10,
double_q=args.double_q,
noisy=args.noisy,
attack=args.attack)
approximate_num_iters = args.num_steps / 4
exploration = PiecewiseSchedule([(0, 1.0),
(approximate_num_iters / 50, 0.1),
(approximate_num_iters / 5, 0.01)],
outside_value=0.01)
if args.prioritized:
replay_buffer = PrioritizedReplayBuffer(args.replay_buffer_size,
args.prioritized_alpha)
beta_schedule = LinearSchedule(approximate_num_iters,
initial_p=args.prioritized_beta0,
final_p=1.0)
else:
replay_buffer = ReplayBuffer(args.replay_buffer_size)
U.initialize()
update_target()
num_iters = 0
# Create training graph and replay buffer
act, train, update_target, debug, craft_adv = deepq.build_train(
make_obs_ph=lambda name: U.Uint8Input(env.observation_space.shape, name=name),
q_func=dueling_model if args.dueling else model,
num_actions=env.action_space.n,
optimizer=tf.train.AdamOptimizer(learning_rate=args.lr, epsilon=1e-4),
gamma=0.99,
grad_norm_clipping=10,
double_q=args.double_q,
noisy=args.noisy,
attack = args.attack
)
approximate_num_iters = args.num_steps / 4
exploration = PiecewiseSchedule([
(0, 1.0),
(approximate_num_iters / 50, 0.1),
(approximate_num_iters / 5, 0.01)
], outside_value=0.01)
if args.prioritized:
replay_buffer = PrioritizedReplayBuffer(args.replay_buffer_size, args.prioritized_alpha)
beta_schedule = LinearSchedule(approximate_num_iters, initial_p=args.prioritized_beta0, final_p=1.0)
else:
replay_buffer = ReplayBuffer(args.replay_buffer_size)
U.initialize()
update_target()
num_iters = 0
# Load the model
state = maybe_load_model(savedir, container)
make_obs_ph=lambda name: U.Uint8Input(env.observation_space.shape,
name=name),
q_func=dueling_model if args.dueling else model,
num_actions=env.action_space.n,
optimizer=tf.train.AdamOptimizer(learning_rate=args.lr,
epsilon=1e-4),
gamma=0.99,
grad_norm_clipping=10,
double_q=args.double_q,
noisy=args.noisy,
attack=args.attack
)
approximate_num_iters = args.num_steps / 4
exploration = PiecewiseSchedule([
(0, 1.0),
(approximate_num_iters / 50, 0.1),
(approximate_num_iters / 5, 0.01)
], outside_value=0.01)
if args.prioritized:
replay_buffer = PrioritizedReplayBuffer(args.replay_buffer_size,
args.prioritized_alpha)
beta_schedule = LinearSchedule(approximate_num_iters,
initial_p=args.prioritized_beta0,
final_p=1.0)
else:
replay_buffer = ReplayBuffer(args.replay_buffer_size)
U.initialize()
update_target()
num_iters = 0