tf_agents/agents/ddpg/ddpg_agent.py [243:260]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    with tf.GradientTape(watch_accessed_variables=False) as tape:
      assert trainable_critic_variables, ('No trainable critic variables to '
                                          'optimize.')
      tape.watch(trainable_critic_variables)
      critic_loss = self.critic_loss(time_steps, actions, next_time_steps,
                                     weights=weights, training=True)
    tf.debugging.check_numerics(critic_loss, 'Critic loss is inf or nan.')
    critic_grads = tape.gradient(critic_loss, trainable_critic_variables)
    self._apply_gradients(critic_grads, trainable_critic_variables,
                          self._critic_optimizer)

    trainable_actor_variables = self._actor_network.trainable_variables
    with tf.GradientTape(watch_accessed_variables=False) as tape:
      assert trainable_actor_variables, ('No trainable actor variables to '
                                         'optimize.')
      tape.watch(trainable_actor_variables)
      actor_loss = self.actor_loss(time_steps, weights=weights, training=True)
    tf.debugging.check_numerics(actor_loss, 'Actor loss is inf or nan.')
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



tf_agents/agents/td3/td3_agent.py [289:306]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    with tf.GradientTape(watch_accessed_variables=False) as tape:
      assert trainable_critic_variables, ('No trainable critic variables to '
                                          'optimize.')
      tape.watch(trainable_critic_variables)
      critic_loss = self.critic_loss(time_steps, actions, next_time_steps,
                                     weights=weights, training=True)
    tf.debugging.check_numerics(critic_loss, 'Critic loss is inf or nan.')
    critic_grads = tape.gradient(critic_loss, trainable_critic_variables)
    self._apply_gradients(critic_grads, trainable_critic_variables,
                          self._critic_optimizer)

    trainable_actor_variables = self._actor_network.trainable_variables
    with tf.GradientTape(watch_accessed_variables=False) as tape:
      assert trainable_actor_variables, ('No trainable actor variables to '
                                         'optimize.')
      tape.watch(trainable_actor_variables)
      actor_loss = self.actor_loss(time_steps, weights=weights, training=True)
    tf.debugging.check_numerics(actor_loss, 'Actor loss is inf or nan.')
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -