Related papers: Learning and Equilibrium under Model Misspecificat…

This paper explores the dynamics of learning in a multi-sector general equilibrium model where firms operate under incomplete information about their production returns to scale. Firms iteratively update their beliefs using maximum…

The training of autonomous agents often requires expensive and unsafe trial-and-error interactions with the environment. Nowadays several data sets containing recorded experiences of intelligent agents performing various tasks, spanning…

Learned dynamics models combined with both planning and policy learning algorithms have shown promise in enabling artificial agents to learn to perform many diverse tasks with limited supervision. However, one of the fundamental challenges…

We develop original models to study interacting agents in financial markets and in social networks. Within these models randomness is vital as a form of shock or news that decays with time. Agents learn from their observations and learning…

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…

Modeling the purposeful behavior of imperfect agents from a small number of observations is a challenging task. When restricted to the single-agent decision-theoretic setting, inverse optimal control techniques assume that observed behavior…

We study the in-context learning dynamics of large language models (LLMs) using three instrumental learning tasks adapted from cognitive psychology. We find that LLMs update their beliefs in an asymmetric manner and learn more from…

Deviations from Bayesian updating are traditionally categorized as biases, errors, or fallacies, thus implying their inherent ``sub-optimality.'' We offer a more nuanced view. We demonstrate that, in learning problems with misspecified…

Neural networks are among the most accurate supervised learning methods in use today. However, their opacity makes them difficult to trust in critical applications, especially when conditions in training may differ from those in practice.…

Federated learning distributes model training among a multitude of agents, who, guided by privacy concerns, perform training using their local data but share only model parameter updates, for iterative aggregation at the server. In this…

Targeted Learning is a subfield of statistics that unifies advances in causal inference, machine learning and statistical theory to help answer scientifically impactful questions with statistical confidence. Targeted Learning is driven by…

We study the emergence of conformity preferences in an environment in which agents choose effort under heterogeneous, possibly misspecified returns, and social interactions do not directly affect material payoffs. Some agents choose effort…

We study education as a remedy for misspecified beliefs in a canonical sequential social-learning model. Uneducated agents misinterpret action histories - treating actions as if they were independent signals and, potentially, overstating…

We present novel monotone comparative statics results for steady-state behavior in a dynamic optimization environment with misspecified Bayesian learning. Building on \cite{ep21a}, we analyze a Bayesian learner whose prior is over…

By planning through a learned dynamics model, model-based reinforcement learning (MBRL) offers the prospect of good performance with little environment interaction. However, it is common in practice for the learned model to be inaccurate,…

Machine learning algorithms are increasingly used to inform critical decisions. There is a growing concern about bias, that algorithms may produce uneven outcomes for individuals in different demographic groups. In this work, we measure…

This work provides a rigorous framework for studying continuous time control problems in uncertain environments. The framework considered models uncertainty in state dynamics as a measure on the space of functions. This measure is…

In scientific machine learning, models are routinely deployed with parameter values or boundary conditions far from those used in training. This paper studies the learning-where-to-learn problem of designing a training data distribution…

We introduce and formalize misalignment, a phenomenon of interactive environments perceived from an analyst's perspective where an agent holds beliefs about another agent's beliefs that do not correspond to the actual beliefs of the latter.…

The rapid deployment of Large Language Models and AI agents across critical societal and technical domains is hindered by persistent behavioral pathologies including sycophancy, hallucination, and strategic deception that resist mitigation…