arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1606.04671cs.LG
收藏

渐进式神经网络

Progressive Neural Networks

Google DeepMind(谷歌DeepMind)

Andrei A. Rusu, Neil C. Rabinowitz, Guillaume Desjardins, Hubert Soyer, James Kirkpatrick, Koray Kavukcuoglu, Razvan Pascanu, Raia Hadsell

摘要:

学习解决复杂的任务序列-同时利用转移和避免灾难性遗忘-仍然是实现人类智能的关键障碍。渐进式网络方法代表了在这个方向上向前迈出的一步:它们不受遗忘的影响,并且可以通过与先前学习的特征的横向连接来利用先验知识。我们在各种各样的强化学习任务(Atari和3D迷宫游戏)上广泛评估了这种架构,并表明它优于基于预训练和微调的常见基线。使用一种新的敏感性措施,我们表明,转让发生在低级别的感官和高级别的控制层的学习政策。

英文摘要:

Learning to solve complex sequences of tasks--while both leveraging transfer and avoiding catastrophic forgetting--remains a key obstacle to achieving human-level intelligence. The progressive networks approach represents a step forward in this direction: they are immune to forgetting and can leverage prior knowledge via lateral connections to previously learned features. We evaluate this architecture extensively on a wide variety of reinforcement learning tasks (Atari and 3D maze games), and show that it outperforms common baselines based on pretraining and finetuning. Using a novel sensitivity measure, we demonstrate that transfer occurs at both low-level sensory and high-level control layers of the learned policy.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑