dodox/fancy_gym
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

fixed incorrect sampling in hole reacher

Browse Source
This commit is contained in:
ottofabian 2021-05-19 18:02:34 +02:00
parent 724b8c6c61
commit 17c489d622
1 changed files with 5 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
alr_envs/classic_control/hole_reacher.py
View File

@ -105,8 +105,8 @@ class HoleReacherEnv(MPEnv):
return self._get_obs().copy() return self._get_obs().copy()
def _generate_hole(self): def _generate_hole(self):
self._tmp_hole_x = self.np_random.uniform(0.5, 3.5, 1) if self._hole_x is None else np.copy(self._hole_x) self._tmp_hole_x = self.np_random.uniform(1, 3.5, 1) if self._hole_x is None else np.copy(self._hole_x)
self._tmp_hole_width = self.np_random.uniform(0.5, 0.1, 1) if self._hole_width is None else np.copy( self._tmp_hole_width = self.np_random.uniform(0.15, 0.5, 1) if self._hole_width is None else np.copy(
self._hole_width) self._hole_width)
# TODO we do not want this right now. # TODO we do not want this right now.
self._tmp_hole_depth = self.np_random.uniform(1, 1, 1) if self._hole_depth is None else np.copy( self._tmp_hole_depth = self.np_random.uniform(1, 1, 1) if self._hole_depth is None else np.copy(
@ -310,11 +310,12 @@ if __name__ == '__main__':
hole_depth=1, hole_x=None) hole_depth=1, hole_x=None)
obs = env.reset() obs = env.reset()
for i in range(200): for i in range(2000):
# objective.load_result("/tmp/cma") # objective.load_result("/tmp/cma")
# test with random actions # test with random actions
ac = 2 * env.action_space.sample() ac = 2 * env.action_space.sample()
obs, rew, d, info = env.step(ac) obs, rew, d, info = env.step(ac)
if i % 10 == 0:
env.render(mode=render_mode) env.render(mode=render_mode)
print(rew) print(rew)