gryf/coach
1
0
Fork 0
mirror of https://github.com/gryf/coach.git synced 2025-12-17 19:20:19 +01:00
Code Issues Projects Releases Wiki Activity

allow specifying gym environments via entry point syntax: module.package:class

Browse Source
This commit is contained in:
Zach Dwiel
2018-01-10 10:14:23 -05:00
parent 93a54c7e8e
commit cc76a9ad70
1 changed files with 12 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
environments/gym_environment_wrapper.py
View File

@@ -48,7 +48,11 @@ class GymEnvironmentWrapper(EnvironmentWrapper):
EnvironmentWrapper.__init__(self, tuning_parameters) EnvironmentWrapper.__init__(self, tuning_parameters)
# env parameters # env parameters
self.env = gym.make(self.env_id) if ':' in self.env_id:
self.env = gym.envs.registration.load(self.env_id)()
else:
self.env = gym.make(self.env_id)
if self.seed is not None: if self.seed is not None:
self.env.seed(self.seed) self.env.seed(self.seed)
@@ -91,11 +95,14 @@ class GymEnvironmentWrapper(EnvironmentWrapper):
self.key_to_action = self.env.unwrapped.get_keys_to_action() self.key_to_action = self.env.unwrapped.get_keys_to_action()
# measurements # measurements
self.timestep_limit = self.env.spec.timestep_limit if self.env.spec is not None:
self.timestep_limit = self.env.spec.timestep_limit
else:
self.timestep_limit = None
self.measurements_size = len(self.step(0)['info'].keys()) self.measurements_size = len(self.step(0)['info'].keys())
def _update_state(self): def _update_state(self):
if hasattr(self.env.env, 'ale'): if hasattr(self.env, 'env') and hasattr(self.env.env, 'ale'):
if self.phase == RunPhase.TRAIN and hasattr(self, 'current_ale_lives'): if self.phase == RunPhase.TRAIN and hasattr(self, 'current_ale_lives'):
# signal termination for life loss # signal termination for life loss
if self.current_ale_lives != self.env.env.ale.lives(): if self.current_ale_lives != self.env.env.ale.lives():
@@ -134,7 +141,7 @@ class GymEnvironmentWrapper(EnvironmentWrapper):
def _restart_environment_episode(self, force_environment_reset=False): def _restart_environment_episode(self, force_environment_reset=False):
# prevent reset of environment if there are ale lives left # prevent reset of environment if there are ale lives left
if (hasattr(self.env.env, 'ale') and self.env.env.ale.lives() > 0) \ if (hasattr(self.env, 'env') and hasattr(self.env.env, 'ale') and self.env.env.ale.lives() > 0) \
and not force_environment_reset and not self.env._past_limit(): and not force_environment_reset and not self.env._past_limit():
return self.observation return self.observation