def testComputeActionFeasibility(self):
constraint_net = DummyNet(self._observation_spec, self._action_spec)
quantile_constraint = constraints.QuantileConstraint(
self._time_step_spec,
self._action_spec,
constraint_network=constraint_net)
init_op = quantile_constraint.initialize()
if not tf.executing_eagerly():
with self.cached_session() as sess:
common.initialize_uninitialized_variables(sess)
self.assertIsNone(sess.run(init_op))
observation = tf.constant([[1, 2], [3, 4]], dtype=tf.float32)
feasibility_prob = quantile_constraint(observation)
self.assertAllGreaterEqual(self.evaluate(feasibility_prob), 0.0)
self.assertAllLessEqual(self.evaluate(feasibility_prob), 1.0)
def testCreateConstraint(self):
constraint_net = DummyNet(self._observation_spec, self._action_spec)
constraints.QuantileConstraint(
self._time_step_spec,
self._action_spec,
constraint_network=constraint_net)