mirror of
https://github.com/Farama-Foundation/Gymnasium.git
synced 2025-08-18 21:06:59 +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>
59 lines
1.8 KiB
Python
59 lines
1.8 KiB
Python
from typing import Optional
|
|
|
|
import numpy as np
|
|
|
|
from gym import utils
|
|
from gym.envs.mujoco import mujoco_env
|
|
|
|
|
|
class InvertedDoublePendulumEnv(mujoco_env.MujocoEnv, utils.EzPickle):
|
|
def __init__(self, render_mode: Optional[str] = None):
|
|
mujoco_env.MujocoEnv.__init__(
|
|
self,
|
|
"inverted_double_pendulum.xml",
|
|
5,
|
|
render_mode=render_mode,
|
|
mujoco_bindings="mujoco_py",
|
|
)
|
|
utils.EzPickle.__init__(self)
|
|
|
|
def step(self, action):
|
|
self.do_simulation(action, self.frame_skip)
|
|
|
|
self.renderer.render_step()
|
|
|
|
ob = self._get_obs()
|
|
x, _, y = self.sim.data.site_xpos[0]
|
|
dist_penalty = 0.01 * x**2 + (y - 2) ** 2
|
|
v1, v2 = self.sim.data.qvel[1:3]
|
|
vel_penalty = 1e-3 * v1**2 + 5e-3 * v2**2
|
|
alive_bonus = 10
|
|
r = alive_bonus - dist_penalty - vel_penalty
|
|
done = bool(y <= 1)
|
|
return ob, r, done, {}
|
|
|
|
def _get_obs(self):
|
|
return np.concatenate(
|
|
[
|
|
self.sim.data.qpos[:1], # cart x pos
|
|
np.sin(self.sim.data.qpos[1:]), # link angles
|
|
np.cos(self.sim.data.qpos[1:]),
|
|
np.clip(self.sim.data.qvel, -10, 10),
|
|
np.clip(self.sim.data.qfrc_constraint, -10, 10),
|
|
]
|
|
).ravel()
|
|
|
|
def reset_model(self):
|
|
self.set_state(
|
|
self.init_qpos
|
|
+ self.np_random.uniform(low=-0.1, high=0.1, size=self.model.nq),
|
|
self.init_qvel + self.np_random.standard_normal(self.model.nv) * 0.1,
|
|
)
|
|
return self._get_obs()
|
|
|
|
def viewer_setup(self):
|
|
v = self.viewer
|
|
v.cam.trackbodyid = 0
|
|
v.cam.distance = self.model.stat.extent * 0.5
|
|
v.cam.lookat[2] = 0.12250000000000005 # v.model.stat.center[2]
|