mirror of
https://github.com/Farama-Foundation/Gymnasium.git
synced 2025-08-25 07:48:30 +00:00
9acf9cd367
* add pygame GUI for frozen_lake.py env * add new line at EOF * pre-commit reformat * improve graphics * new images and dynamic window size * darker tile borders and fix ICC profile * pre-commit hook * adjust elf and stool size * Update frozen_lake.py * reformat * fix #2600 * #2600 * add rgb_array support * reformat * test render api change on FrozenLake * add render support for reset on frozenlake * add clock on pygame render * new render api for blackjack * new render api for cliffwalking * new render api for Env class * update reset method, lunar and Env * fix wrapper * fix reset lunar * new render api for box2d envs * new render api for mujoco envs * fix bug * new render api for classic control envs * fix tests * add render_mode None for CartPole * new render api for test fake envs * pre-commit hook * fix FrozenLake * fix FrozenLake * more render_mode to super - frozenlake * remove kwargs from frozen_lake new * pre-commit hook * add deprecated render method * add backwards compatibility * fix test * add _render * move pygame.init() (avoid pygame dependency on init) * fix pygame dependencies * remove collect_render() maintain multi-behaviours .render() * add type hints * fix renderer * don't call .render() with None * improve docstring * add single_rgb_array to all envs * remove None from metadata["render_modes"] * add type hints to test_env_checkers * fix lint * add comments to renderer * add comments to single_depth_array and single_state_pixels * reformat * add deprecation warnings and env.render_mode declaration * fix lint * reformat * fix tests * add docs * fix car racing determinism * remove warning test envs, customizable modes on renderer * remove commments and add todo for env_checker * fix car racing * replace render mode check with assert * update new mujoco * reformat * reformat * change metaclass definition * fix tests * implement mark suggestions (test, docs, sets) * check_render Co-authored-by: J K Terry <jkterry0@gmail.com>
65 lines
2.0 KiB
Python
65 lines
2.0 KiB
Python
from typing import Optional
|
|
|
|
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, render_mode: Optional[str] = None):
|
|
mujoco_env.MujocoEnv.__init__(
|
|
self, "ant.xml", 5, render_mode=render_mode, mujoco_bindings="mujoco_py"
|
|
)
|
|
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]
|
|
|
|
self.renderer.render_step()
|
|
|
|
forward_reward = (xposafter - xposbefore) / self.dt
|
|
ctrl_cost = 0.5 * 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=-0.1, high=0.1
|
|
)
|
|
qvel = self.init_qvel + self.np_random.standard_normal(self.model.nv) * 0.1
|
|
self.set_state(qpos, qvel)
|
|
return self._get_obs()
|
|
|
|
def viewer_setup(self):
|
|
self.viewer.cam.distance = self.model.stat.extent * 0.5
|