Understanding Model Selection For Learning In Strategic Environments

Abstract

The deployment of ever-larger machine learning models reflects a growing consensus that the more expressive the model class one optimizes over\(\unicode\{x2013\}\)and the more data one has access to\(\unicode\{x2013\}\)the more one can improve performance. As models get deployed in a variety of real-world scenarios, they inevitably face strategic environments. In this work, we consider the natural question of how the interplay of models and strategic interactions affects the relationship between performance at equilibrium and the expressivity of model classes. We find that strategic interactions can break the conventional view\(\unicode\{x2013\}\)meaning that performance does not necessarily monotonically improve as model classes get larger or more expressive (even with infinite data). We show the implications of this result in several contexts including strategic regression, strategic classification, and multi-agent reinforcement learning. In particular, we show that each of these set

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyhandina2024understanding

Related papers

• Practical Performative Policy Learning With Strategic Agents (2024)0.00
• Improved Training Mechanism For Reinforcement Learning Via Online Model Selection (2025)0.00
• Scaling Behaviors Of LLM Reinforcement Learning Post-training: An Empirical Study In Mathematical Reasoning (2025)0.00
• Model Selection In Batch Policy Optimization (2021)0.00
• Learning To Design Games: Strategic Environments In Reinforcement Learning (2017)0.00
• Double Meta-learning For Data Efficient Policy Optimization In Non-stationary Environments (2020)0.00
• Model-agnostic Solutions For Deep Reinforcement Learning In Non-ergodic Contexts (2026)0.00
• World Models As An Intermediary Between Agents And The Real World (2026)0.00