Active Evaluation of General Agents: Problem Definition and Comparison of Baseline Algorithms

TL;DR

This paper introduces a formal framework for active, online evaluation of general agents across multiple tasks, comparing baseline algorithms like Elo and Soft Condorcet, and demonstrating their effectiveness in different contexts.

Contribution

It proposes a novel online evaluation framework for agents that adaptively samples tasks and agents, and compares baseline ranking algorithms within this setting.

Findings

Elo rating system is reliable for ranking reduction in practice.

Soft Condorcet Optimization outperforms Elo on real Atari data.

Task selection based on proportional representation improves ranking accuracy.

Abstract

As intelligent agents become more generally-capable, i.e. able to master a wide variety of tasks, the complexity and cost of properly evaluating them rises significantly. Tasks that assess specific capabilities of the agents can be correlated and stochastic, requiring many samples for accurate comparisons, leading to added costs. In this paper, we propose a formal definition and a conceptual framework for active evaluation of agents across multiple tasks, which assesses the performance of ranking algorithms as a function of number of evaluation data samples. Rather than curating, filtering, or compressing existing data sets as a preprocessing step, we propose an online framing: on every iteration, the ranking algorithm chooses the task and agents to sample scores from. Then, evaluation algorithms report a ranking of agents on each iteration and their performance is assessed with respect to the ground truth ranking over time. Several baselines are compared under different experimental contexts, with synthetic generated data and simulated online access to real evaluation data from Atari game-playing agents. We find that the classical Elo rating system -- while it suffers from well-known failure modes, in theory -- is a consistently reliable choice for efficient reduction of ranking error in practice. A recently-proposed method, Soft Condorcet Optimization, shows comparable performance to Elo on synthetic data and significantly outperforms Elo on real Atari agent evaluation. When task variation from the ground truth is high, selecting tasks based on proportional representation leads to higher rate of ranking error reduction.