mirror of
https://github.com/Farama-Foundation/Gymnasium.git
synced 2025-09-02 02:32:50 +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>
60 lines
1.8 KiB
Python
60 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 ReacherEnv(mujoco_env.MujocoEnv, utils.EzPickle):
|
|
def __init__(self, render_mode: Optional[str] = None):
|
|
utils.EzPickle.__init__(self)
|
|
mujoco_env.MujocoEnv.__init__(
|
|
self, "reacher.xml", 2, render_mode=render_mode, mujoco_bindings="mujoco_py"
|
|
)
|
|
|
|
def step(self, a):
|
|
vec = self.get_body_com("fingertip") - self.get_body_com("target")
|
|
reward_dist = -np.linalg.norm(vec)
|
|
reward_ctrl = -np.square(a).sum()
|
|
reward = reward_dist + reward_ctrl
|
|
self.do_simulation(a, self.frame_skip)
|
|
|
|
self.renderer.render_step()
|
|
|
|
ob = self._get_obs()
|
|
done = False
|
|
return ob, reward, done, dict(reward_dist=reward_dist, reward_ctrl=reward_ctrl)
|
|
|
|
def viewer_setup(self):
|
|
self.viewer.cam.trackbodyid = 0
|
|
|
|
def reset_model(self):
|
|
qpos = (
|
|
self.np_random.uniform(low=-0.1, high=0.1, size=self.model.nq)
|
|
+ self.init_qpos
|
|
)
|
|
while True:
|
|
self.goal = self.np_random.uniform(low=-0.2, high=0.2, size=2)
|
|
if np.linalg.norm(self.goal) < 0.2:
|
|
break
|
|
qpos[-2:] = self.goal
|
|
qvel = self.init_qvel + self.np_random.uniform(
|
|
low=-0.005, high=0.005, size=self.model.nv
|
|
)
|
|
qvel[-2:] = 0
|
|
self.set_state(qpos, qvel)
|
|
return self._get_obs()
|
|
|
|
def _get_obs(self):
|
|
theta = self.sim.data.qpos.flat[:2]
|
|
return np.concatenate(
|
|
[
|
|
np.cos(theta),
|
|
np.sin(theta),
|
|
self.sim.data.qpos.flat[2:],
|
|
self.sim.data.qvel.flat[:2],
|
|
self.get_body_com("fingertip") - self.get_body_com("target"),
|
|
]
|
|
)
|