Spaces:
Running
Running
File size: 3,669 Bytes
375a1cf |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 |
__credits__ = ["Rushiv Arora"]
import numpy as np
from gym import utils
from gym.envs.mujoco import MuJocoPyEnv
from gym.spaces import Box
DEFAULT_CAMERA_CONFIG = {
"distance": 4.0,
}
class HalfCheetahEnv(MuJocoPyEnv, utils.EzPickle):
metadata = {
"render_modes": [
"human",
"rgb_array",
"depth_array",
],
"render_fps": 20,
}
def __init__(
self,
xml_file="half_cheetah.xml",
forward_reward_weight=1.0,
ctrl_cost_weight=0.1,
reset_noise_scale=0.1,
exclude_current_positions_from_observation=True,
**kwargs
):
utils.EzPickle.__init__(
self,
xml_file,
forward_reward_weight,
ctrl_cost_weight,
reset_noise_scale,
exclude_current_positions_from_observation,
**kwargs
)
self._forward_reward_weight = forward_reward_weight
self._ctrl_cost_weight = ctrl_cost_weight
self._reset_noise_scale = reset_noise_scale
self._exclude_current_positions_from_observation = (
exclude_current_positions_from_observation
)
if exclude_current_positions_from_observation:
observation_space = Box(
low=-np.inf, high=np.inf, shape=(17,), dtype=np.float64
)
else:
observation_space = Box(
low=-np.inf, high=np.inf, shape=(18,), dtype=np.float64
)
MuJocoPyEnv.__init__(
self, xml_file, 5, observation_space=observation_space, **kwargs
)
def control_cost(self, action):
control_cost = self._ctrl_cost_weight * np.sum(np.square(action))
return control_cost
def step(self, action):
x_position_before = self.sim.data.qpos[0]
self.do_simulation(action, self.frame_skip)
x_position_after = self.sim.data.qpos[0]
x_velocity = (x_position_after - x_position_before) / self.dt
ctrl_cost = self.control_cost(action)
forward_reward = self._forward_reward_weight * x_velocity
observation = self._get_obs()
reward = forward_reward - ctrl_cost
terminated = False
info = {
"x_position": x_position_after,
"x_velocity": x_velocity,
"reward_run": forward_reward,
"reward_ctrl": -ctrl_cost,
}
if self.render_mode == "human":
self.render()
return observation, reward, terminated, False, info
def _get_obs(self):
position = self.sim.data.qpos.flat.copy()
velocity = self.sim.data.qvel.flat.copy()
if self._exclude_current_positions_from_observation:
position = position[1:]
observation = np.concatenate((position, velocity)).ravel()
return observation
def reset_model(self):
noise_low = -self._reset_noise_scale
noise_high = self._reset_noise_scale
qpos = self.init_qpos + self.np_random.uniform(
low=noise_low, high=noise_high, size=self.model.nq
)
qvel = (
self.init_qvel
+ self._reset_noise_scale * self.np_random.standard_normal(self.model.nv)
)
self.set_state(qpos, qvel)
observation = self._get_obs()
return observation
def viewer_setup(self):
assert self.viewer is not None
for key, value in DEFAULT_CAMERA_CONFIG.items():
if isinstance(value, np.ndarray):
getattr(self.viewer.cam, key)[:] = value
else:
setattr(self.viewer.cam, key, value)
|