Home
last modified time | relevance | path

Searched refs:action_space (Results 1 – 25 of 113) sorted by relevance

12345

/dports/math/py-gym/gym-0.21.0/gym/utils/
H A Denv_checker.py54 action = env.action_space.sample()
146 if np.any(np.equal(action_space.low, action_space.high)):
148 if np.any(np.greater(action_space.low, action_space.high)):
150 if action_space.low.shape != action_space.shape:
152 if action_space.high.shape != action_space.shape:
158 np.any(np.abs(action_space.low) != np.abs(action_space.high))
159 or np.any(np.abs(action_space.low) > 1)
190 action = action_space.sample()
305 action_space = env.action_space
307 env.step(env.action_space.sample())
[all …]
/dports/math/py-gym/gym-0.21.0/gym/wrappers/
H A Drescale_action.py18 env.action_space, spaces.Box
19 ), "expected Box action space, got {}".format(type(env.action_space))
24 np.zeros(env.action_space.shape, dtype=env.action_space.dtype) + min_action
27 np.zeros(env.action_space.shape, dtype=env.action_space.dtype) + max_action
29 self.action_space = spaces.Box(
32 shape=env.action_space.shape,
33 dtype=env.action_space.dtype,
42 low = self.env.action_space.low
43 high = self.env.action_space.high
H A Dclip_action.py10 assert isinstance(env.action_space, Box)
14 return np.clip(action, self.action_space.low, self.action_space.high)
/dports/misc/mxnet/incubator-mxnet-1.9.0/example/reinforcement-learning/ddpg/
H A Dstrategies.py46 self.action_space = env_spec.action_space
47 self.state = np.ones(self.action_space.flat_dim) * self.mu
59 self.state = np.ones(self.action_space.flat_dim) * self.mu
69 self.action_space.low,
70 self.action_space.high)
78 self.action_space = Env2()
/dports/misc/py-mxnet/incubator-mxnet-1.9.0/example/reinforcement-learning/ddpg/
H A Dstrategies.py46 self.action_space = env_spec.action_space
47 self.state = np.ones(self.action_space.flat_dim) * self.mu
59 self.state = np.ones(self.action_space.flat_dim) * self.mu
69 self.action_space.low,
70 self.action_space.high)
78 self.action_space = Env2()
/dports/devel/py-bullet3/bullet3-3.21/examples/pybullet/gym/pybullet_envs/minitaur/agents/tools/
H A Dwrappers_test.py46 env.step(env.action_space.sample())
47 env.step(env.action_space.sample())
54 env.step(env.action_space.sample())
60 env.step(env.action_space.sample())
61 env.step(env.action_space.sample())
63 env.step(env.action_space.sample())
H A Dbatch_env.py45 action_space = self._envs[0].action_space
46 if not all(env.action_space == action_space for env in self._envs):
82 if not env.action_space.contains(action):
H A Dwrappers.py90 action = self._env.action_space.sample()
200 self._is_finite(self._env.action_space))
217 def action_space(self): member in RangeNormalize
218 space = self._env.action_space
238 min_ = self._env.action_space.low
239 max_ = self._env.action_space.high
263 def action_space(self): member in ClipAction
264 shape = self._env.action_space.shape
268 action_space = self._env.action_space
269 action = np.clip(action, action_space.low, action_space.high)
[all …]
H A Dmock_algorithm.py38 shape = (len(self._envs),) + self._envs[0].action_space.shape
39 low = self._envs[0].action_space.low
40 high = self._envs[0].action_space.high
/dports/math/py-gym/gym-0.21.0/gym/vector/
H A Dsync_vector_env.py32 def __init__(self, env_fns, observation_space=None, action_space=None, copy=True): argument
38 if (observation_space is None) or (action_space is None):
40 action_space = action_space or self.envs[0].action_space
44 action_space=action_space,
H A Dvector_env.py32 def __init__(self, num_envs, observation_space, action_space): argument
37 self.action_space = Tuple((action_space,) * num_envs)
45 self.single_action_space = action_space
/dports/devel/py-bullet3/bullet3-3.21/examples/pybullet/gym/pybullet_envs/minitaur/envs_v2/env_wrappers/
H A Daction_denormalize_wrapper.py10 low = np.array(env.action_space.low)
11 high = np.array(env.action_space.high)
22 self.action_space = gym.spaces.Box(
25 shape=self._gym_env.action_space.low.shape,
/dports/devel/py-bullet3/bullet3-3.21/examples/pybullet/gym/pybullet_envs/agents/tools/
H A Dbatch_env.py45 action_space = self._envs[0].action_space
46 if not all(env.action_space == action_space for env in self._envs):
81 if not env.action_space.contains(action):
H A Dwrappers.py92 action = self._env.action_space.sample()
202 self._is_finite(self._env.action_space))
219 def action_space(self): member in RangeNormalize
220 space = self._env.action_space
240 min_ = self._env.action_space.low
241 max_ = self._env.action_space.high
265 def action_space(self): member in ClipAction
266 shape = self._env.action_space.shape
270 action_space = self._env.action_space
271 action = np.clip(action, action_space.low, action_space.high)
[all …]
H A Dmock_algorithm.py40 shape = (tf.shape(agent_indices)[0],) + self._envs[0].action_space.shape
41 low = self._envs[0].action_space.low
42 high = self._envs[0].action_space.high
/dports/devel/py-bullet3/bullet3-3.21/examples/pybullet/gym/pybullet_envs/minitaur/envs_v2/sensors/
H A Dspace_utils.py120 def create_constant_action(action_space, action_value=0): argument
122 if isinstance(action_space, gym.spaces.Dict):
126 for sub_name, sub_space in action_space.spaces.items()
129 return np.full(action_space.shape, action_value)
/dports/math/py-gym/gym-0.21.0/gym/
H A Dcore.py38 action_space = None variable in Env
249 def action_space(self): member in Wrapper
251 return self.env.action_space
254 @action_space.setter
255 def action_space(self, space): member in Wrapper
/dports/devel/py-bullet3/bullet3-3.21/examples/pybullet/gym/pybullet_envs/examples/
H A Denjoy_TF_HalfCheetahBulletEnv_v0_2017may.py20 def __init__(self, observation_space, action_space): argument
23 assert weights_final_w.shape == (64, action_space.shape[0])
37 pi = SmallReactivePolicy(env.observation_space, env.action_space)
H A Denjoy_TF_HopperBulletEnv_v0_2017may.py22 def __init__(self, observation_space, action_space): argument
25 assert weights_final_w.shape == (64, action_space.shape[0])
39 pi = SmallReactivePolicy(env.observation_space, env.action_space)
H A Denjoy_TF_Walker2DBulletEnv_v0_2017may.py20 def __init__(self, observation_space, action_space): argument
23 assert weights_final_w.shape == (64, action_space.shape[0])
36 pi = SmallReactivePolicy(env.observation_space, env.action_space)
H A Denjoy_TF_InvertedPendulumBulletEnv_v0_2017may.py20 def __init__(self, observation_space, action_space): argument
23 assert weights_final_w.shape == (32, action_space.shape[0])
37 pi = SmallReactivePolicy(env.observation_space, env.action_space)
H A Denjoy_TF_InvertedPendulumSwingupBulletEnv_v0_2017may.py20 def __init__(self, observation_space, action_space): argument
23 assert weights_final_w.shape == (32.0, action_space.shape[0])
37 pi = SmallReactivePolicy(env.observation_space, env.action_space)
H A Denjoy_TF_AntBulletEnv_v0_2017may.py20 def __init__(self, observation_space, action_space): argument
23 assert weights_final_w.shape == (64, action_space.shape[0])
38 pi = SmallReactivePolicy(env.observation_space, env.action_space)
H A Denjoy_TF_HumanoidBulletEnv_v0_2017may.py20 def __init__(self, observation_space, action_space): argument
23 assert weights_final_w.shape == (128, action_space.shape[0])
37 pi = SmallReactivePolicy(env.observation_space, env.action_space)
H A Denjoy_TF_InvertedDoublePendulumBulletEnv_v0_2017may.py20 def __init__(self, observation_space, action_space): argument
23 assert weights_final_w.shape == (32.0, action_space.shape[0])
37 pi = SmallReactivePolicy(env.observation_space, env.action_space)

12345