All sequential decision-making agents explore so as to acquire knowledge about a particular target. It is often the responsibility of the agent designer to construct this target which, in rich and complex environments, constitutes a onerous burden; without full knowledge of the environment itself, a designer may forge a sub-optimal learning target that poorly balances the amount of information an agent must acquire to identify the target against the target's associated performance shortfall. While recent work has developed a connection between learning targets and rate-distortion theory to address this challenge and empower agents that decide what to learn in an automated fashion, the proposed algorithm does not optimally tackle the equally important challenge of efficient information acquisition. In this work, building upon the seminal design principle of information-directed sampling (Russo & Van Roy, 2014), we address this shortcoming directly to couple optimal information acquisition with the optimal design of learning targets. Along the way, we offer new insights into learning targets from the literature on rate-distortion theory before turning to empirical results that confirm the value of information when deciding what to learn.

Incentive design deals with interaction between a principal and an agent where the former can shape the latter's utility through a policy commitment. It is well known that the principal faces an information rent when dealing with an agent that has informational advantage. In this work, we embark on a systematic study of the effect of information asymmetry in incentive design games. Specifically, we first demonstrate that it is in principal's interest to decrease this information asymmetry. To mitigate this uncertainty, we let the principal gather information either by letting the agent shape her belief (aka Information Design), or by paying to acquire it. Providing solutions to all these cases we show that while introduction of uncertainty increases the principal's cost, letting the agent shape its belief can be advantageous. We study information asymmetry and information acquisition in both matrix games and quadratic Gaussian game setups.

Sensory training during the early ages is vital for human development. Inspired by this cognitive phenomenon, we observe that the early training stage is also important for the multimodal learning process, where dataset information is rapidly acquired. We refer to this stage as the prime learning window. However, based on our observation, this prime learning window in multimodal learning is often dominated by information-sufficient modalities, which in turn suppresses the information acquisition of information-insufficient modalities. To address this issue, we propose Information Acquisition Regulation (InfoReg), a method designed to balance information acquisition among modalities. Specifically, InfoReg slows down the information acquisition process of information-sufficient modalities during the prime learning window, which could promote information acquisition of information-insufficient modalities. This regulation enables a more balanced learning process and improves the overall performance of the multimodal network. Experiments show that InfoReg outperforms related multimodal imbalanced methods across various datasets, achieving superior model performance. The code is available at https://github.com/GeWu-Lab/InfoReg_CVPR2025.

All sequential decision-making agents explore so as to acquire knowledge about a particular target. It is often the responsibility of the agent designer to construct this target which, in rich and complex environments, constitutes a onerous burden; without full knowledge of the environment itself, a designer may forge a sub-optimal learning target that poorly balances the amount of information an agent must acquire to identify the target against the target's associated performance shortfall. While recent work has developed a connection between learning targets and rate-distortion theory to address this challenge and empower agents that decide what to learn in an automated fashion, the proposed algorithm does not optimally tackle the equally important challenge of efficient information acquisition. In this work, building upon the seminal design principle of information-directed sampling (Russo & Van Roy, 2014), we address this shortcoming directly to couple optimal information acquisition with the optimal design of learning targets. Along the way, we offer new insights into learning targets from the literature on rate-distortion theory before turning to empirical results that confirm the value of information when deciding what to learn.

We design and train machine learning models to capture the nonlinear interactions between financial market dynamics and high-frequency trading (HFT) activity. In doing so, we introduce new metrics to identify liquidity-demanding and -supplying HFT strategies. Both types of HFT strategies increase activity in response to information events and decrease it when trading speed is restricted, with liquidity-supplying strategies demonstrating greater responsiveness. Liquidity-demanding HFT is positively linked with latency arbitrage opportunities, whereas liquidity-supplying HFT is negatively related, aligning with theoretical expectations. Our metrics have implications for understanding the information production process in financial markets.

The distributed coordination of robot teams performing complex tasks is challenging to formulate. The different aspects of a complete task such as local planning for obstacle avoidance, global goal coordination and collaborative mapping are often solved separately, when clearly each of these should influence the others for the most efficient behaviour. In this paper we use the example application of distributed information acquisition as a robot team explores a large space to show that we can formulate the whole problem as a single factor graph with multiple connected layers representing each aspect. We use Gaussian Belief Propagation (GBP) as the inference mechanism, which permits parallel, on-demand or asynchronous computation for efficiency when different aspects are more or less important. This is the first time that a distributed GBP multi-robot solver has been proven to enable intelligent collaborative behaviour rather than just guiding robots to individual, selfish goals. We encourage the reader to view our demos at https://aalpatya.github.io/gbpstack

Training and education are imperative in many facets of healthcare -- from understanding clinical systems, to improving technical skills, to understanding regulations and professional standards. Technology often presents unique training challenges because of the ways in which it disrupts existing workflow patterns, alters clinical practice, and creates both predictable and unforeseen challenges. The emergence of artificial intelligence (AI), its anticipated expansion in healthcare, and its sheer scope point to significant training and educational needs for medical students and practicing healthcare providers. These needs go far beyond developing technical skills with AI programs and systems; rather, they call for a shift in the paradigm of medical learning. An AMA Journal of Ethics article titled "Reimagining Medical Education in the Age of AI" discusses how traditional medical education -- which focuses on information acquisition, retention, and application -- is insufficient, counterproductive, and potentially harmful in the era of digital medicine.

Bounded rationality is an important consideration stemming from the fact that agents often have limits on their processing abilities, making the assumption of perfect rationality inapplicable to many real tasks. We propose an information-theoretic approach to the inference of agent decisions under Smithian competition. The model explicitly captures the boundedness of agents (limited in their information-processing capacity) as the cost of information acquisition for expanding their prior beliefs. The expansion is measured as the Kullblack-Leibler divergence between posterior decisions and prior beliefs. When information acquisition is free, the \textit{homo economicus} agent is recovered, while in cases when information acquisition becomes costly, agents instead revert to their prior beliefs. The maximum entropy principle is used to infer least-biased decisions, based upon the notion of Smithian competition formalised within the Quantal Response Statistical Equilibrium framework. The incorporation of prior beliefs into such a framework allowed us to systematically explore the effects of prior beliefs on decision-making, in the presence of market feedback. We verified the proposed model using Australian housing market data, showing how the incorporation of prior knowledge alters the resulting agent decisions. Specifically, it allowed for the separation (and analysis) of past beliefs and utility maximisation behaviour of the agent.

Attention control is a key cognitive ability for humans to select information relevant to the current task. This paper develops a computational model of attention and an algorithm for attention-based probabilistic planning in Markov decision processes. In attention-based planning, the robot decides to be in different attention modes. An attention mode corresponds to a subset of state variables monitored by the robot. By switching between different attention modes, the robot actively perceives task-relevant information to reduce the cost of information acquisition and processing, while achieving near-optimal task performance. Though planning with attention-based active perception inevitably introduces partial observations, a partially observable MDP formulation makes the problem computational expensive to solve. Instead, our proposed method employs a hierarchical planning framework in which the robot determines what to pay attention to and for how long the attention should be sustained before shifting to other information sources. During the attention sustaining phase, the robot carries out a sub-policy, computed from an abstraction of the original MDP given the current attention. We use an example where a robot is tasked to capture a set of intruders in a stochastic gridworld. The experimental results show that the proposed method enables information- and computation-efficient optimal planning in stochastic environments.