A Domain-Agnostic Approach for Characterization of Lifelong Learning Systems

• URL: http://arxiv.org/abs/2301.07799v1
• Date: Wed, 18 Jan 2023 21:58:54 GMT
• Title: A Domain-Agnostic Approach for Characterization of Lifelong Learning Systems
• Authors: Megan M. Baker, Alexander New, Mario Aguilar-Simon, Ziad Al-Halah, S\'ebastien M. R. Arnold, Ese Ben-Iwhiwhu, Andrew P. Brna, Ethan Brooks, Ryan C. Brown, Zachary Daniels, Anurag Daram, Fabien Delattre, Ryan Dellana, Eric Eaton, Haotian Fu, Kristen Grauman, Jesse Hostetler, Shariq Iqbal, Cassandra Kent, Nicholas Ketz, Soheil Kolouri, George Konidaris, Dhireesha Kudithipudi, Erik Learned-Miller, Seungwon Lee, Michael L. Littman, Sandeep Madireddy, Jorge A. Mendez, Eric Q. Nguyen, Christine D. Piatko, Praveen K. Pilly, Aswin Raghavan, Abrar Rahman, Santhosh Kumar Ramakrishnan, Neale Ratzlaff, Andrea Soltoggio, Peter Stone, Indranil Sur, Zhipeng Tang, Saket Tiwari, Kyle Vedder, Felix Wang, Zifan Xu, Angel Yanguas-Gil, Harel Yedidsion, Shangqun Yu, Gautam K. Vallabha
• Abstract summary: "Lifelong Learning" systems are capable of 1) Continuous Learning, 2) Transfer and Adaptation, and 3) Scalability. We show that this suite of metrics can inform the development of varied and complex Lifelong Learning systems.
• Score: 128.63953314853327
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Despite the advancement of machine learning techniques in recent years, state-of-the-art systems lack robustness to "real world" events, where the input distributions and tasks encountered by the deployed systems will not be limited to the original training context, and systems will instead need to adapt to novel distributions and tasks while deployed. This critical gap may be addressed through the development of "Lifelong Learning" systems that are capable of 1) Continuous Learning, 2) Transfer and Adaptation, and 3) Scalability. Unfortunately, efforts to improve these capabilities are typically treated as distinct areas of research that are assessed independently, without regard to the impact of each separate capability on other aspects of the system. We instead propose a holistic approach, using a suite of metrics and an evaluation framework to assess Lifelong Learning in a principled way that is agnostic to specific domains or system techniques. Through five case studies, we show that this suite of metrics can inform the development of varied and complex Lifelong Learning systems. We highlight how the proposed suite of metrics quantifies performance trade-offs present during Lifelong Learning system development - both the widely discussed Stability-Plasticity dilemma and the newly proposed relationship between Sample Efficient and Robust Learning. Further, we make recommendations for the formulation and use of metrics to guide the continuing development of Lifelong Learning systems and assess their progress in the future.

Related papers

• Temporal-Difference Variational Continual Learning [89.32940051152782]
  A crucial capability of Machine Learning models in real-world applications is the ability to continuously learn new tasks. In Continual Learning settings, models often struggle to balance learning new tasks with retaining previous knowledge. We propose new learning objectives that integrate the regularization effects of multiple previous posterior estimations.
  arXiv  Detail & Related papers  (2024-10-10T10:58:41Z)
• Evaluating and Improving Continual Learning in Spoken Language Understanding [58.723320551761525]
  We propose an evaluation methodology that provides a unified evaluation on stability, plasticity, and generalizability in continual learning. By employing the proposed metric, we demonstrate how introducing various knowledge distillations can improve different aspects of these three properties of the SLU model.
  arXiv  Detail & Related papers  (2024-02-16T03:30:27Z)
• Epistemic Exploration for Generalizable Planning and Learning in Non-Stationary Settings [23.038187032666304]
  This paper introduces a new approach for continual planning and model learning in non-stationary environments. The proposed framework models gaps in the agent's current state of knowledge and uses them to conduct focused, investigative explorations. Empirical evaluations on several non-stationary benchmark domains show that this approach significantly outperforms planning and RL baselines in terms of sample complexity.
  arXiv  Detail & Related papers  (2024-02-13T00:50:06Z)
• Evaluating Pretrained models for Deployable Lifelong Learning [15.56002252251323]
  We evaluate a Deployable Lifelong Learning system for Visual Reinforcement Learning (RL) that is pretrained on a curated dataset. We show that this system can be scaled to incorporate a large number of tasks due to the small memory footprint and fewer computational resources.
  arXiv  Detail & Related papers  (2023-11-22T19:04:05Z)
• L2Explorer: A Lifelong Reinforcement Learning Assessment Environment [49.40779372040652]
  Reinforcement learning solutions tend to generalize poorly when exposed to new tasks outside of the data distribution they are trained on. We introduce a framework for continual reinforcement-learning development and assessment using Lifelong Learning Explorer (L2Explorer) L2Explorer is a new, Unity-based, first-person 3D exploration environment that can be continuously reconfigured to generate a range of tasks and task variants structured into complex evaluation curricula.
  arXiv  Detail & Related papers  (2022-03-14T19:20:26Z)
• Assessing the State of Self-Supervised Human Activity Recognition using Wearables [6.777825307593778]
  Self-supervised learning in the field of wearables-based human activity recognition (HAR) Self-supervised methods enable a host of new application domains such as, for example, domain adaptation and transfer across sensor positions, activities etc.
  arXiv  Detail & Related papers  (2022-02-22T02:21:50Z)
• Lifelong Learning Metrics [63.8376359764052]
  The DARPA Lifelong Learning Machines (L2M) program seeks to yield advances in artificial intelligence (AI) systems. This document outlines a formalism for constructing and characterizing the performance of agents performing lifelong learning scenarios.
  arXiv  Detail & Related papers  (2022-01-20T16:29:14Z)
• Towards a theory of out-of-distribution learning [23.878004729029644]
  We propose a chronological approach to defining different learning tasks using the provably approximately correct (PAC) learning framework. We will start with in-distribution learning and progress to recently proposed lifelong or continual learning. Our hope is that this work will inspire a universally agreed-upon approach to quantifying different types of learning.
  arXiv  Detail & Related papers  (2021-09-29T15:35:16Z)
• Active Learning for Nonlinear System Identification with Guarantees [102.43355665393067]
  We study a class of nonlinear dynamical systems whose state transitions depend linearly on a known feature embedding of state-action pairs. We propose an active learning approach that achieves this by repeating three steps: trajectory planning, trajectory tracking, and re-estimation of the system from all available data. We show that our method estimates nonlinear dynamical systems at a parametric rate, similar to the statistical rate of standard linear regression.
  arXiv  Detail & Related papers  (2020-06-18T04:54:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.