A collective AI via lifelong learning and sharing at the edge

A Soltoggio, E Ben-Iwhiwhu, V Braverman… - Nature Machine …, 2024‏ - nature.com
One vision of a future artificial intelligence (AI) is where many separate units can learn
independently over a lifetime and share their knowledge with each other. The synergy …

How to reuse and compose knowledge for a lifetime of tasks: A survey on continual learning and functional composition

JA Mendez, E Eaton - ar** and composition in entropy-regularized reinforcement learning
J Adamczyk, A Arriojas, S Tiomkin… - Proceedings of the AAAI …, 2023‏ - ojs.aaai.org
In reinforcement learning (RL), the ability to utilize prior knowledge from previously solved
tasks can allow agents to quickly solve new problems. In some cases, these new problems …

Lifelong reinforcement learning with temporal logic formulas and reward machines

X Zheng, C Yu, M Zhang - Knowledge-Based Systems, 2022‏ - Elsevier
Continuously learning new tasks using high-level ideas or knowledge is a key capability of
humans. In this paper, we propose lifelong reinforcement learning with sequential linear …

Run-time task composition with safety semantics

K Leahy, M Mann, Z Serlin - Forty-first International Conference on …, 2024‏ - openreview.net
Compositionality is a critical aspect of scalable system design. Here, we focus on Boolean
composition of learned tasks as opposed to functional or sequential composition. Existing …