Publication | Open Access
Progressive Neural Networks
1.1K
Citations
0
References
2016
Year
Artificial IntelligenceIncremental LearningEngineeringMachine LearningSequential LearningProgressive NetworksLearning ControlLifelong Reinforcement LearningRecurrent Neural NetworkProgressive Neural NetworksSocial SciencesCatastrophic ForgettingComplex SequencesMemoryRobot LearningCognitive ScienceAutonomous LearningComputer ScienceDeep LearningProcedural MemoryNeuroscienceContinual Learning (Educational Psychology)
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.