def test_unflatten(self):
env = TheanoEnv(
normalize(gym.make('Blackjack-v0'),
normalize_reward=True,
normalize_obs=True,
flatten_obs=False))
for i in range(10):
env.reset()
for e in range(5):
action = env.action_space.sample()
next_obs, reward, done, info = env.step(action)
assert (env.observation_space.flatten(next_obs).shape ==
env.observation_space.flat_dim) # yapf: disable
if done:
break
env.close()
def test_flatten(self):
env = TheanoEnv(
normalize(gym.make('Pendulum-v0'),
normalize_reward=True,
normalize_obs=True,
flatten_obs=True))
for i in range(10):
env.reset()
for e in range(5):
env.render()
action = env.action_space.sample()
next_obs, reward, done, info = env.step(action)
assert next_obs.shape == env.observation_space.low.shape
if done:
break
env.close()
observation = env.reset()
for _ in range(T):
# policy.get_action() returns a pair of values. The second
# one returns a dictionary, whose values contains
# sufficient statistics for the action distribution. It
# should at least contain entries that would be returned
# by calling policy.dist_info(), which is the non-symbolic
# analog of policy.dist_info_sym(). Storing these
# statistics is useful, e.g., when forming importance
# sampling ratios. In our case it is not needed.
action, _ = policy.get_action(observation)
# Recall that the last entry of the tuple stores diagnostic
# information about the environment. In our case it is not needed.
next_observation, reward, terminal, _ = env.step(action)
observations.append(observation)
actions.append(action)
rewards.append(reward)
observation = next_observation
if terminal:
# Finish rollout if terminal state reached
break
# We need to compute the empirical return for each time step along the
# trajectory
path = dict(
observations=np.array(observations),
actions=np.array(actions),
rewards=np.array(rewards),
)
