mirror of
https://github.com/Farama-Foundation/Gymnasium.git
synced 2025-08-30 01:50:19 +00:00
4c460ba6c8
* add dtype to Box
* remove board_game, debugging, safety, parameter_tuning environments
* massive set of breaking changes
- remove python logging module
- _step, _reset, _seed, _close => non underscored method
- remove benchmark and scoring folder
* Improve render("human"), now resizable, closable window.
* get rid of default step and reset in wrappers, so it doesn’t silently fail for people with underscore methods
* CubeCrash unit test environment
* followup fixes
* MemorizeDigits unit test envrionment
* refactored spaces a bit
fixed indentation
disabled test_env_semantics
* fix unit tests
* fixes
* CubeCrash, MemorizeDigits tested
* gym backwards compatibility patch
* gym backwards compatibility, followup fixes
* changelist, add spaces to main namespaces
* undo_logger_setup for backwards compat
* remove configuration.py
41 lines
1.4 KiB
Python
41 lines
1.4 KiB
Python
import numpy as np
|
|
from gym import utils
|
|
from gym.envs.mujoco import mujoco_env
|
|
|
|
class HopperEnv(mujoco_env.MujocoEnv, utils.EzPickle):
|
|
def __init__(self):
|
|
mujoco_env.MujocoEnv.__init__(self, 'hopper.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()
|
|
s = self.state_vector()
|
|
done = not (np.isfinite(s).all() and (np.abs(s[2:]) < 100).all() and
|
|
(height > .7) and (abs(ang) < .2))
|
|
ob = self._get_obs()
|
|
return ob, reward, done, {}
|
|
|
|
def _get_obs(self):
|
|
return np.concatenate([
|
|
self.sim.data.qpos.flat[1:],
|
|
np.clip(self.sim.data.qvel.flat, -10, 10)
|
|
])
|
|
|
|
def reset_model(self):
|
|
qpos = self.init_qpos + self.np_random.uniform(low=-.005, high=.005, size=self.model.nq)
|
|
qvel = self.init_qvel + self.np_random.uniform(low=-.005, high=.005, size=self.model.nv)
|
|
self.set_state(qpos, qvel)
|
|
return self._get_obs()
|
|
|
|
def viewer_setup(self):
|
|
self.viewer.cam.trackbodyid = 2
|
|
self.viewer.cam.distance = self.model.stat.extent * 0.75
|
|
self.viewer.cam.lookat[2] += .8
|
|
self.viewer.cam.elevation = -20
|