MCPcopy Create free account
hub / github.com/google-deepmind/dm_control / get_reward

Method get_reward

dm_control/composer/task.py:277–286  ·  view source on GitHub ↗

Calculates the reward signal given the physics state. Args: physics: A Physics object. Returns: A float

(self, physics)

Source from the content-addressed store, hash-verified

275
276 @abc.abstractmethod
277 def get_reward(self, physics):
278 """Calculates the reward signal given the physics state.
279
280 Args:
281 physics: A Physics object.
282
283 Returns:
284 A float
285 """
286 raise NotImplementedError
287
288 def should_terminate_episode(self, physics): # pylint: disable=unused-argument
289 """Determines whether the episode should terminate given the physics state.

Callers 1

stepMethod · 0.45

Calls

no outgoing calls

Tested by

no test coverage detected