93d87b907ff5ef42753492c79e602b31f9e7df00,chainerrl/agents/categorical_dqn.py,CategoricalDQN,_compute_loss,#CategoricalDQN#Any#Any#Any#,128

Before Change

        // Minimize the cross entropy
        // y is clipped to avoid log(0)
        eltwise_loss = -t * F.log(F.clip(y, 1e-10, 1.))
        if self.batch_accumulator == "sum":
            loss = F.sum(eltwise_loss)
        else:
            loss = F.mean(F.sum(eltwise_loss, axis=1))
        return loss

After Change

        if errors_out is not None:
            del errors_out[:]
            delta = F.sum(eltwise_loss, axis=1)
            delta = cuda.to_cpu(delta.array)
            for e in delta:
                errors_out.append(e)

        if "weights" in exp_batch:
            return compute_weighted_value_loss(
                y, t, exp_batch["weights"],
                clip_delta=self.clip_delta,

Instances