Analysis of the Memorization and Generalization Capabilities of AI Agents: Are Continual Learners Robust?

TL;DR

This paper introduces a novel continual learning framework that enhances robustness to unseen environments by balancing memorization and generalization, supported by theoretical analysis and superior experimental results.

Contribution

It proposes a new CL method using capacity-limited memory and risk distribution estimation to improve robustness and generalization in dynamic environments.

Findings

Outperforms existing memory-based CL baselines.

Shows improved generalization on unseen environments.

Analyzes the tradeoff between memorization and generalization.

Abstract

In continual learning (CL), an AI agent (e.g., autonomous vehicles or robotics) learns from non-stationary data streams under dynamic environments. For the practical deployment of such applications, it is important to guarantee robustness to unseen environments while maintaining past experiences. In this paper, a novel CL framework is proposed to achieve robust generalization to dynamic environments while retaining past knowledge. The considered CL agent uses a capacity-limited memory to save previously observed environmental information to mitigate forgetting issues. Then, data points are sampled from the memory to estimate the distribution of risks over environmental change so as to obtain predictors that are robust with unseen changes. The generalization and memorization performance of the proposed framework are theoretically analyzed. This analysis showcases the tradeoff between memorization and generalization with the memory size. Experiments show that the proposed algorithm outperforms memory-based CL baselines across all environments while significantly improving the generalization performance on unseen target environments.