Continual Learning Without Knowing Task Identities: Rethinking Occam's Razor

no code implementations • 1 Jan 2021 • Tiffany Tuor, Shiqiang Wang, Kin Leung

Due to the catastrophic forgetting phenomenon of deep neural networks (DNNs), models trained in standard ways tend to forget what it has learned from previous tasks, especially when the new task is sufficiently different from the previous ones.

Continual Learning Model Selection

Jointly-Trained State-Action Embedding for Efficient Reinforcement Learning

no code implementations • 28 Sep 2020 • Paul Julian Pritz, Liang Ma, Kin Leung

Model-free reinforcement learning approaches use some form of state representations and the latest work has explored embedding techniques for actions, both with the aim of achieving better generalization and applicability.

Model-based Reinforcement Learning Recommendation Systems +2