mirror of
https://github.com/Farama-Foundation/Gymnasium.git
synced 2025-08-23 15:04:20 +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
46 lines
1.6 KiB
Python
46 lines
1.6 KiB
Python
import numpy as np
|
|
from gym import utils
|
|
from gym.envs.mujoco import mujoco_env
|
|
|
|
class AntEnv(mujoco_env.MujocoEnv, utils.EzPickle):
|
|
def __init__(self):
|
|
mujoco_env.MujocoEnv.__init__(self, 'ant.xml', 5)
|
|
utils.EzPickle.__init__(self)
|
|
|
|
def step(self, a):
|
|
xposbefore = self.get_body_com("torso")[0]
|
|
self.do_simulation(a, self.frame_skip)
|
|
xposafter = self.get_body_com("torso")[0]
|
|
forward_reward = (xposafter - xposbefore)/self.dt
|
|
ctrl_cost = .5 * np.square(a).sum()
|
|
contact_cost = 0.5 * 1e-3 * np.sum(
|
|
np.square(np.clip(self.sim.data.cfrc_ext, -1, 1)))
|
|
survive_reward = 1.0
|
|
reward = forward_reward - ctrl_cost - contact_cost + survive_reward
|
|
state = self.state_vector()
|
|
notdone = np.isfinite(state).all() \
|
|
and state[2] >= 0.2 and state[2] <= 1.0
|
|
done = not notdone
|
|
ob = self._get_obs()
|
|
return ob, reward, done, dict(
|
|
reward_forward=forward_reward,
|
|
reward_ctrl=-ctrl_cost,
|
|
reward_contact=-contact_cost,
|
|
reward_survive=survive_reward)
|
|
|
|
def _get_obs(self):
|
|
return np.concatenate([
|
|
self.sim.data.qpos.flat[2:],
|
|
self.sim.data.qvel.flat,
|
|
np.clip(self.sim.data.cfrc_ext, -1, 1).flat,
|
|
])
|
|
|
|
def reset_model(self):
|
|
qpos = self.init_qpos + self.np_random.uniform(size=self.model.nq, low=-.1, high=.1)
|
|
qvel = self.init_qvel + self.np_random.randn(self.model.nv) * .1
|
|
self.set_state(qpos, qvel)
|
|
return self._get_obs()
|
|
|
|
def viewer_setup(self):
|
|
self.viewer.cam.distance = self.model.stat.extent * 0.5
|