mirror of
https://github.com/Farama-Foundation/Gymnasium.git
synced 2025-08-29 17:45:07 +00:00
58e6aa95e5
* Make environments seedable * Fix monitor bugs - Set monitor_id before setting the infix. This was a bug that would yield incorrect results with multiple monitors. - Remove extra pid from stats recorder filename. This should be purely cosmetic. * Start uploading seeds in episode_batch * Fix _bigint_from_bytes for python3 * Set seed explicitly in random_agent * Pass through seed argument * Also pass through random state to spaces * Pass random state into the observation/action spaces * Make all _seed methods return the list of used seeds * Switch over to np.random where possible * Start hashing seeds, and also seed doom engine * Fixup seeding determinism in many cases * Seed before loading the ROM * Make seeding more Python3 friendly * Make the MuJoCo skipping a bit more forgiving * Remove debugging PDB calls * Make setInt argument into raw bytes * Validate and upload seeds * Skip box2d * Make seeds smaller, and change representation of seeds in upload * Handle long seeds * Fix RandomAgent example to be deterministic * Handle integer types correctly in Python2 and Python3 * Try caching pip * Try adding swap * Add df and free calls * Bump swap * Bump swap size * Try setting overcommit * Try other sysctls * Try fixing overcommit * Try just setting overcommit_memory=1 * Add explanatory comment * Add what's new section to readme * BUG: Mark ElevatorAction-ram-v0 as non-deterministic for now * Document seed * Move nondetermistic check into spec
35 lines
1.2 KiB
Python
35 lines
1.2 KiB
Python
import numpy as np
|
|
from gym import utils
|
|
from gym.envs.mujoco import mujoco_env
|
|
|
|
class HalfCheetahEnv(mujoco_env.MujocoEnv, utils.EzPickle):
|
|
def __init__(self):
|
|
mujoco_env.MujocoEnv.__init__(self, 'half_cheetah.xml', 5)
|
|
utils.EzPickle.__init__(self)
|
|
|
|
def _step(self, action):
|
|
xposbefore = self.model.data.qpos[0,0]
|
|
self.do_simulation(action, self.frame_skip)
|
|
xposafter = self.model.data.qpos[0,0]
|
|
ob = self._get_obs()
|
|
reward_ctrl = - 0.1 * np.square(action).sum()
|
|
reward_run = (xposafter - xposbefore)/self.dt
|
|
reward = reward_ctrl + reward_run
|
|
done = False
|
|
return ob, reward, done, dict(reward_run = reward_run, reward_ctrl=reward_ctrl)
|
|
|
|
def _get_obs(self):
|
|
return np.concatenate([
|
|
self.model.data.qpos.flat[1:],
|
|
self.model.data.qvel.flat,
|
|
])
|
|
|
|
def reset_model(self):
|
|
qpos = self.init_qpos + self.np_random.uniform(low=-.1, high=.1, size=self.model.nq)
|
|
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
|