Progressive Neural Networks
This addresses a key obstacle in achieving human-level intelligence for AI systems by enabling learning across tasks without forgetting.
The paper tackled the problem of catastrophic forgetting and transfer learning in sequential tasks by introducing progressive networks, which outperformed pretraining and finetuning baselines on reinforcement learning tasks like Atari and 3D maze games, showing transfer at both sensory and control layers.
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.