mirror of
https://github.com/Farama-Foundation/Gymnasium.git
synced 2025-08-01 06:07:08 +00:00
e913bc81b8
* feat: add `isort` to `pre-commit` * ci: skip `__init__.py` file for `isort` * ci: make `isort` mandatory in lint pipeline * docs: add a section on Git hooks * ci: check isort diff * fix: isort from master branch * docs: add pre-commit badge * ci: update black + bandit versions * feat: add PR template * refactor: PR template * ci: remove bandit * docs: add Black badge * ci: try to remove all `|| true` statements * ci: remove lint_python job - Remove `lint_python` CI job - Move `pyupgrade` job to `pre-commit` workflow * fix: avoid messing with typing * docs: add a note on running `pre-cpmmit` manually * ci: apply `pre-commit` to the whole codebase
43 lines
1.4 KiB
Python
43 lines
1.4 KiB
Python
import numpy as np
|
|
|
|
from gym import utils
|
|
from gym.envs.mujoco import mujoco_env
|
|
|
|
|
|
class Walker2dEnv(mujoco_env.MujocoEnv, utils.EzPickle):
|
|
def __init__(self):
|
|
mujoco_env.MujocoEnv.__init__(self, "walker2d.xml", 4)
|
|
utils.EzPickle.__init__(self)
|
|
|
|
def step(self, a):
|
|
posbefore = self.sim.data.qpos[0]
|
|
self.do_simulation(a, self.frame_skip)
|
|
posafter, height, ang = self.sim.data.qpos[0:3]
|
|
alive_bonus = 1.0
|
|
reward = (posafter - posbefore) / self.dt
|
|
reward += alive_bonus
|
|
reward -= 1e-3 * np.square(a).sum()
|
|
done = not (height > 0.8 and height < 2.0 and ang > -1.0 and ang < 1.0)
|
|
ob = self._get_obs()
|
|
return ob, reward, done, {}
|
|
|
|
def _get_obs(self):
|
|
qpos = self.sim.data.qpos
|
|
qvel = self.sim.data.qvel
|
|
return np.concatenate([qpos[1:], np.clip(qvel, -10, 10)]).ravel()
|
|
|
|
def reset_model(self):
|
|
self.set_state(
|
|
self.init_qpos
|
|
+ self.np_random.uniform(low=-0.005, high=0.005, size=self.model.nq),
|
|
self.init_qvel
|
|
+ self.np_random.uniform(low=-0.005, high=0.005, size=self.model.nv),
|
|
)
|
|
return self._get_obs()
|
|
|
|
def viewer_setup(self):
|
|
self.viewer.cam.trackbodyid = 2
|
|
self.viewer.cam.distance = self.model.stat.extent * 0.5
|
|
self.viewer.cam.lookat[2] = 1.15
|
|
self.viewer.cam.elevation = -20
|