Revealing the Learning Process in Reinforcement Learning Agents Through Attention-Oriented Metrics
This work addresses the gap in understanding RL agent learning processes for researchers, though it is incremental as it builds on existing attention and behavioral analysis methods.
The authors tackled the problem of understanding the learning process in reinforcement learning agents by introducing attention-oriented metrics (ATOMs) to track attention development during training, finding that ATOMs delineated attention patterns across game variations and revealed consistent developmental phases.
The learning process of a reinforcement learning (RL) agent remains poorly understood beyond the mathematical formulation of its learning algorithm. To address this gap, we introduce attention-oriented metrics (ATOMs) to investigate the development of an RL agent's attention during training. In a controlled experiment, we tested ATOMs on three variations of a Pong game, each designed to teach the agent distinct behaviours, complemented by a behavioural assessment. ATOMs successfully delineate the attention patterns of an agent trained on each game variation, and that these differences in attention patterns translate into differences in the agent's behaviour. Through continuous monitoring of ATOMs during training, we observed that the agent's attention developed in phases, and that these phases were consistent across game variations. Overall, we believe that ATOM could help improve our understanding of the learning processes of RL agents and better understand the relationship between attention and learning.