def _compute_y_and_t(self, exp_batch):
batch_state = exp_batch['state']
batch_size = len(batch_state)
# Compute Q-values for current states
qout = self.q_function(batch_state)
batch_actions = exp_batch['action']
batch_q = F.reshape(qout.evaluate_actions(batch_actions),
(batch_size, 1))
# Target values must also backprop gradients
batch_q_target = F.reshape(self._compute_target_values(exp_batch),
(batch_size, 1))
return batch_q, scale_grad.scale_grad(batch_q_target, self.grad_scale)
def _compute_y_and_t(self, exp_batch):
batch_state = exp_batch['state']
# Compute Q-values for current states
if self.recurrent:
qout, _ = self.model.n_step_forward(batch_state,
exp_batch['recurrent_state'],
output_mode='concat')
else:
qout = self.model(batch_state)
batch_actions = exp_batch['action']
batch_q = qout.evaluate_actions(batch_actions)[..., None]
# Target values must also backprop gradients
batch_q_target = self._compute_target_values(exp_batch)[..., None]
return batch_q, scale_grad.scale_grad(batch_q_target, self.grad_scale)