179 lines
5.2 KiB
Python
179 lines
5.2 KiB
Python
__credits__ = ["Rushiv Arora"]
|
|
|
|
import numpy as np
|
|
|
|
from gymnasium import utils
|
|
from gymnasium.envs.mujoco import MuJocoPyEnv
|
|
from gymnasium.spaces import Box
|
|
|
|
|
|
DEFAULT_CAMERA_CONFIG = {
|
|
"trackbodyid": 2,
|
|
"distance": 3.0,
|
|
"lookat": np.array((0.0, 0.0, 1.15)),
|
|
"elevation": -20.0,
|
|
}
|
|
|
|
|
|
class HopperEnv(MuJocoPyEnv, utils.EzPickle):
|
|
metadata = {
|
|
"render_modes": [
|
|
"human",
|
|
"rgb_array",
|
|
"depth_array",
|
|
],
|
|
"render_fps": 125,
|
|
}
|
|
|
|
def __init__(
|
|
self,
|
|
xml_file="hopper.xml",
|
|
forward_reward_weight=1.0,
|
|
ctrl_cost_weight=1e-3,
|
|
healthy_reward=1.0,
|
|
terminate_when_unhealthy=True,
|
|
healthy_state_range=(-100.0, 100.0),
|
|
healthy_z_range=(0.7, float("inf")),
|
|
healthy_angle_range=(-0.2, 0.2),
|
|
reset_noise_scale=5e-3,
|
|
exclude_current_positions_from_observation=True,
|
|
**kwargs,
|
|
):
|
|
utils.EzPickle.__init__(
|
|
self,
|
|
xml_file,
|
|
forward_reward_weight,
|
|
ctrl_cost_weight,
|
|
healthy_reward,
|
|
terminate_when_unhealthy,
|
|
healthy_state_range,
|
|
healthy_z_range,
|
|
healthy_angle_range,
|
|
reset_noise_scale,
|
|
exclude_current_positions_from_observation,
|
|
**kwargs,
|
|
)
|
|
|
|
self._forward_reward_weight = forward_reward_weight
|
|
|
|
self._ctrl_cost_weight = ctrl_cost_weight
|
|
|
|
self._healthy_reward = healthy_reward
|
|
self._terminate_when_unhealthy = terminate_when_unhealthy
|
|
|
|
self._healthy_state_range = healthy_state_range
|
|
self._healthy_z_range = healthy_z_range
|
|
self._healthy_angle_range = healthy_angle_range
|
|
|
|
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=(11,), dtype=np.float64
|
|
)
|
|
else:
|
|
observation_space = Box(
|
|
low=-np.inf, high=np.inf, shape=(12,), dtype=np.float64
|
|
)
|
|
|
|
MuJocoPyEnv.__init__(
|
|
self, xml_file, 4, observation_space=observation_space, **kwargs
|
|
)
|
|
|
|
@property
|
|
def healthy_reward(self):
|
|
return (
|
|
float(self.is_healthy or self._terminate_when_unhealthy)
|
|
* self._healthy_reward
|
|
)
|
|
|
|
def control_cost(self, action):
|
|
control_cost = self._ctrl_cost_weight * np.sum(np.square(action))
|
|
return control_cost
|
|
|
|
@property
|
|
def is_healthy(self):
|
|
z, angle = self.sim.data.qpos[1:3]
|
|
state = self.state_vector()[2:]
|
|
|
|
min_state, max_state = self._healthy_state_range
|
|
min_z, max_z = self._healthy_z_range
|
|
min_angle, max_angle = self._healthy_angle_range
|
|
|
|
healthy_state = np.all(np.logical_and(min_state < state, state < max_state))
|
|
healthy_z = min_z < z < max_z
|
|
healthy_angle = min_angle < angle < max_angle
|
|
|
|
is_healthy = all((healthy_state, healthy_z, healthy_angle))
|
|
|
|
return is_healthy
|
|
|
|
@property
|
|
def terminated(self):
|
|
terminated = not self.is_healthy if self._terminate_when_unhealthy else False
|
|
return terminated
|
|
|
|
def _get_obs(self):
|
|
position = self.sim.data.qpos.flat.copy()
|
|
velocity = np.clip(self.sim.data.qvel.flat.copy(), -10, 10)
|
|
|
|
if self._exclude_current_positions_from_observation:
|
|
position = position[1:]
|
|
|
|
observation = np.concatenate((position, velocity)).ravel()
|
|
return observation
|
|
|
|
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
|
|
healthy_reward = self.healthy_reward
|
|
|
|
rewards = forward_reward + healthy_reward
|
|
costs = ctrl_cost
|
|
|
|
observation = self._get_obs()
|
|
reward = rewards - costs
|
|
terminated = self.terminated
|
|
info = {
|
|
"x_position": x_position_after,
|
|
"x_velocity": x_velocity,
|
|
}
|
|
|
|
if self.render_mode == "human":
|
|
self.render()
|
|
return observation, reward, terminated, False, info
|
|
|
|
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.np_random.uniform(
|
|
low=noise_low, high=noise_high, size=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)
|