Progress & Compress: A scalable framework for continual learning
This addresses the challenge of continual learning for AI systems that need to learn tasks sequentially without forgetting, though it appears incremental as it builds on existing distillation and consolidation techniques.
The paper tackles the problem of catastrophic forgetting in continual learning by introducing a two-component framework that preserves performance on previous tasks while accelerating learning on new ones, demonstrating effectiveness on classification and reinforcement learning domains including Atari games and 3D maze navigation.
We introduce a conceptually simple and scalable framework for continual learning domains where tasks are learned sequentially. Our method is constant in the number of parameters and is designed to preserve performance on previously encountered tasks while accelerating learning progress on subsequent problems. This is achieved by training a network with two components: A knowledge base, capable of solving previously encountered problems, which is connected to an active column that is employed to efficiently learn the current task. After learning a new task, the active column is distilled into the knowledge base, taking care to protect any previously acquired skills. This cycle of active learning (progression) followed by consolidation (compression) requires no architecture growth, no access to or storing of previous data or tasks, and no task-specific parameters. We demonstrate the progress & compress approach on sequential classification of handwritten alphabets as well as two reinforcement learning domains: Atari games and 3D maze navigation.