Revealing The Learning Process In Reinforcement Learning Agents Through Attention-oriented Metrics

Abstract

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 at

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keybeylier2024revealing

Related papers

• Machine Versus Human Attention In Deep Reinforcement Learning Tasks (2020)0.00
• Visualizing And Understanding Atari Agents (2017)0.00
• An Approach To Partial Observability In Games: Learning To Both Act And Observe (2021)3.58
• Interpretable Learning Dynamics In Unsupervised Reinforcement Learning (2025)0.00
• Hackatari: Atari Learning Environments For Robust And Continual Reinforcement Learning (2024)0.00
• Can You See How I Learn? Human Observers' Inferences About Reinforcement Learning Agents' Learning Processes (2025)0.00
• Learn To Interpret Atari Agents (2018)0.00
• A Review For Deep Reinforcement Learning In Atari:benchmarks, Challenges, And Solutions (2021)0.00