def WrappedLabCoreSyncEnv(lab_core_id, fps=60, rewarder_observation=False):
spec = lab.spec(lab_core_id)
env = lab_core_sync.LabCoreSync(BlockingReset(wrap(envs.VNCEnv(fps=fps))))
if rewarder_observation:
env = LabCoreObservation(env, lab_core_id=lab_core_id)
elif spec._entry_point.startswith('lab.envs.atari:'):
env = CropAtari(env)
return env
def create_env(env_id, client_id, remotes, **kwargs):
spec = lab.spec(env_id)
if spec.tags.get('flashgames', False):
return create_flash_env(env_id, client_id, remotes, **kwargs)
elif spec.tags.get('atari', False) and spec.tags.get('vnc', False):
return create_vncatari_env(env_id, client_id, remotes, **kwargs)
else:
# Assume atari.
assert "." not in env_id # institute environments have dots in names.
return create_atari_env(env_id)
def __init__(self, lab_core_id, fps=60, vnc_pixels=True):
super(LabCoreSyncEnv, self).__init__(lab_core_id, fps=fps)
# Metadata has already been cloned
self.metadata['semantics.async'] = False
self.lab_core_id = lab_core_id
self.vnc_pixels = vnc_pixels
if not vnc_pixels:
self._core_env = lab.spec(lab_core_id).make()
else:
self._core_env = None
def __init__(self, env_id):
self.worker_n = None
# Pull the relevant info from a transient env instance
self.spec = lab.spec(env_id)
env = self.spec.make()
current_metadata = self.metadata
self.metadata = env.metadata.copy()
self.metadata.update(current_metadata)
self.action_space = env.action_space
self.observation_space = env.observation_space
self.reward_range = env.reward_range
def __init__(self, env, lab_core_id=None):
super(LabCoreObservation, self).__init__(env)
if lab_core_id is None:
# self.spec is None while inside of the make, so we need
# to pass lab_core_id in explicitly there. This case will
# be hit when instantiating by hand.
lab_core_id = self.spec._kwargs['lab_core_id']
self._reward_n = None
self._done_n = None
self._info_n = None
self._lab_core_env = lab.spec(lab_core_id).make()
def __init__(self, env, lab_core_id=None):
super(LabCoreAction, self).__init__(env)
if lab_core_id is None:
# self.spec is None while inside of the make, so we need
# to pass lab_core_id in explicitly there. This case will
# be hit when instantiating by hand.
lab_core_id = self.spec._kwargs['lab_core_id']
spec = lab.spec(lab_core_id)
raw_action_space = lab_core_action_space(lab_core_id)
self._actions = raw_action_space.actions
self.action_space = lab_spaces.Discrete(len(self._actions))
if spec._entry_point.startswith('lab.envs.atari:'):
self.key_state = translator.AtariKeyState(lab.make(lab_core_id))
else:
self.key_state = None
def lab_core_action_space(lab_core_id):
spec = lab.spec(lab_core_id)
if spec.id == 'CartPole-v0':
return spaces.Hardcoded([[spaces.KeyEvent.by_name('left', down=True)],
[spaces.KeyEvent.by_name('left', down=False)]])
elif spec._entry_point.startswith('lab.envs.atari:'):
actions = []
env = spec.make()
for action in env.unwrapped.get_action_meanings():
z = 'FIRE' in action
left = 'LEFT' in action
right = 'RIGHT' in action
up = 'UP' in action
down = 'DOWN' in action
translated = atari_vnc(up=up, down=down, left=left, right=right, z=z)
actions.append(translated)
return spaces.Hardcoded(actions)
else:
raise error.Error('Unsupported env type: {}'.format(spec.id))
assert vnc_info['stats.reward.count'] == 1
matcher.assert_match(obs,
vnc_obs, {
'reward': reward,
'done': done
},
stage=stage)
count += 1
if done or (timestep_limit is not None and count >= timestep_limit):
break
# TODO: we should have auto-env spinup
specs = [
(lab.spec('lab-core.PongDeterministicSync-v3'), AtariMatcher(),
atari_vnc_wrapper),
(lab.spec('lab-core.PitfallDeterministicSync-v3'), AtariMatcher(),
atari_vnc_wrapper),
# This test is still broken. Looks like we're not piping the seed
# to the CartPole env behind VNC
# (lab.spec('lab-core.CartPoleLowDSync-v0'), CartPoleLowDMatcher())
]
@pytest.mark.parametrize("spec,matcher,wrapper", specs)
def test_nice_vnc_semantics_match(spec, matcher, wrapper):
# Check that when running over VNC or using the raw environment,
# semantics match exactly.
lab.undo_logger_setup()