Related papers: Minimum-Information LQG Control - Part II: Retenti…
A key aspect of many resource allocation problems is the need for the resource controller to compute a function, such as the max or arg max, of the competing users metrics. Information must be exchanged between the competing users and the…
In POMDPs, information about the hidden state, delivered through observations, is both valuable to the agent, allowing it to base its actions on better informed internal states, and a "curse", exploding the size and diversity of the…
The recently proposed set-up of source coding with a side information "vending machine" allows the decoder to select actions in order to control the quality of the side information. The actions can depend on the message received from the…
The quadratic complexity of the attention module makes it gradually become the bulk of compute in Transformer-based LLMs during generation. Moreover, the excessive key-value cache that arises when dealing with long inputs also brings severe…
The problem of controller reduction has a rich history in control theory. Yet, many questions remain open. In particular, there exist very few results on the order reduction of general non-observer based controllers and the subsequent…
Learning and memory are intertwined in our brain and their relationship is at the core of several recent neural network models. In particular, the Attention-Gated MEmory Tagging model (AuGMEnT) is a reinforcement learning network with an…
Today's networks are controlled assuming pre-compressed and packetized data. For video, this assumption of data packets abstracts out one of the key aspects - the lossy compression problem. Therefore, first, this paper develops a framework…
Recurrent transducer models have emerged as a promising solution for speech recognition on the current and next generation smart devices. The transducer models provide competitive accuracy within a reasonable memory footprint alleviating…
Autonomous control systems use various sensors to decrease the amount of uncertainty under which they operate. While providing partial observation of the current state of the system, sensors require resources such as energy, time and…
We study the problem of identifying correlations in multivariate data, under information constraints: Either on the amount of memory that can be used by the algorithm, or the amount of communication when the data is distributed across…
In this paper we study the optimal formation control of multiple agents whose interaction parameters are adjusted upon a cost function consisting of both the control energy and the geometrical performance. By optimizing the interaction…
Regret analysis is challenging in Multi-Agent Reinforcement Learning (MARL) primarily due to the dynamical environments and the decentralized information among agents. We attempt to solve this challenge in the context of decentralized…
The majority of spatial signal processing techniques focus on increasing the total system capacity and providing high data rates for intended user(s). Unlike the existing studies, this paper introduces a novel interference modulation method…
Communication is crucial for solving cooperative Multi-Agent Reinforcement Learning tasks in partially observable Markov Decision Processes. Existing works often rely on black-box methods to encode local information/features into messages…
The goal of this thesis is to design a learning model predictive controller (LMPC) that allows multiple agents to race competitively on a predefined race track in real-time. This thesis addresses two major shortcomings in the already…
AI agents are increasingly used in long, multi-turn workflows in both research and enterprise settings. As interactions grow, agent behavior often degrades due to loss of constraint focus, error accumulation, and memory-induced drift. This…
Central to the functioning of a living cell is its ability to control the readout or expression of information encoded in the genome. In many cases, a single transcription factor protein activates or represses the expression of many genes.…
We propose the interaction of two quantum memristors via capacitive and inductive coupling in feasible superconducting circuit architectures. In this composed system the input gets correlated in time, which changes the dynamic response of…
Memory is a critical component in large language model (LLM)-based agents, enabling them to store and retrieve past executions to improve task performance over time. In this paper, we conduct an empirical study on how memory management…
Decision Transformer-based decision-making agents have shown the ability to generalize across multiple tasks. However, their performance relies on massive data and computation. We argue that this inefficiency stems from the forgetting…