How to Reuse and Compose Knowledge for a Lifetime of Tasks: A Survey on Continual Learning and Functional Composition

2022-07-15 · Jorge A. Mendez, Eric Eaton

A major goal of artificial intelligence (AI) is to create an agent capable of acquiring a general understanding of the world. Such an agent would require the ability to continually accumulate and build upon its knowledge as it encounters new experiences. Lifelong or continual learning addresses this setting, whereby an agent faces a continual stream of problems and must strive to capture the knowledge necessary for solving each new task it encounters. If the agent is capable of accumulating knowledge in some form of compositional representation, it could then selectively reuse and combine relevant pieces of knowledge to construct novel solutions. Despite the intuitive appeal of this simple idea, the literatures on lifelong learning and compositional learning have proceeded largely separately. In an effort to promote developments that bridge between the two fields, this article surveys their respective research landscapes and discusses existing and future connections between them.

📄 PDF Abstract BibTeX arXiv:2207.07730

Code (0)

등록된 구현이 없습니다.

Tasks

Continual LearningLifelong learning

Lifetime policy reuse and the importance of task capacity

2021-06-03 · David M. Bossens, Adam J. Sobey

A long-standing challenge in artificial intelligence is lifelong reinforcement learning, where learners are given many tasks in sequence and must transfer knowledge between tasks while avoiding catastrophic forgetting. P…

reinforcement-learning Reinforcement Learning

Reward Mapping for Transfer in Long-Lived Agents

2013-12-01 · NeurIPS 2013 12 · Xiaoxiao Guo, Satinder Singh, Richard L. Lewis

We consider how to transfer knowledge from previous tasks to a current task in long-lived and bounded agents that must solve a sequence of MDPs over a finite lifetime. A novel aspect of our transfer approach is that we …

Organismal Agency and Rapid Adaptation: The Phenopoiesis Algorithm for Phenotype-First Evolution

2026-02-01 · Nam H. Le arxiv

Evolutionary success depends on the capacity to adapt: organisms must respond to environmental challenges through both genetic innovation and lifetime learning. The gene-centric paradigm attributes evolutionary causality…

Lifelong Reinforcement Learning with Modulating Masks

2022-12-21 · Eseoghene Ben-Iwhiwhu, Saptarshi Nath, Praveen K. Pilly, Soheil Kolouri 외

Lifelong learning aims to create AI systems that continuously and incrementally learn during a lifetime, similar to biological learning. Attempts so far have met problems, including catastrophic forgetting, interference …

Lifelong learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

The Landscape of Ontology Reuse Approaches

2020-11-25 · Valentina Anita Carriero, Marilena Daquino, Aldo Gangemi, Andrea Giovanni Nuzzolese 외

Ontology reuse aims to foster interoperability and facilitate knowledge reuse. Several approaches are typically evaluated by ontology engineers when bootstrapping a new project. However, current practices are often motiv…

Decision Making