Related papers: Thermodynamically rational decision making under u…

Transparency is an essential requirement of machine learning based decision making systems that are deployed in real world. Often, transparency of a given system is achieved by providing explanations of the behavior and predictions of the…

Continuous control and planning remains a major challenge in robotics and machine learning. Neuroscience offers the possibility of learning from animal brains that implement highly successful controllers, but it is unclear how to relate an…

While most of the existing quantum information engines assisted by Maxwell's demon harness thermal fluctuations, those that rectify only quantum fluctuations have recently been constructed. We propose an alternative type of quantum…

Intelligent agents such as robots are increasingly deployed in real-world, safety-critical settings. It is vital that these agents are able to explain the reasoning behind their decisions to human counterparts; however, their behavior is…

This article presents a formal model demonstrating that genuine autonomy, the ability of a system to self-regulate and pursue objectives, fundamentally implies computational unpredictability from an external perspective. we establish…

We have investigated the recently proposed self-consistent theory of fluctuation - induced transport. In this framework the subsystem under study is coupled to two independent baths at different temperatures. In this non-equilibrium system…

Problem definition: Accurately modeling consumer behavior in energy operations is challenging due to uncertainty, behavioral heterogeneity, and limited empirical data-particularly in low-frequency, high-impact events. While generative AI…

Thermodynamics could be seen as an expression of physics at a high epistemic level. As such, its potential as an inductive bias to help machine learning procedures attain accurate and credible predictions has been recently realized in many…

Explanation is necessary for humans to understand and accept decisions made by an AI system when the system's goal is known. It is even more important when the AI system makes decisions in multi-agent environments where the human does not…

Many applications of intelligent systems require reasoning about the mental states of agents in the domain. We may want to reason about an agent's beliefs, including beliefs about other agents; we may also want to reason about an agent's…

Nearly all theoretical analyses of the Maxwell's demon focus on its energetic and entropic costs of operation. Here, we focus on its rate of operation. In our model, a demon's rate limitation stems from its finite response time and gate…

The so-called information-thermodynamics link has been created in a series of works starting from Maxwell demon and established by the idea of transforming information into work in the though experiment of Szilard which then evolved into…

The resolution of the Maxwell's demon paradox linked thermodynamics with information theory through information erasure principle. By considering a demon endowed with a Turing-machine consisting of a memory tape and a processor, we attempt…

Partially observable Markov decision processes (POMDPs) form a prominent model for uncertainty in sequential decision making. We are interested in constructing algorithms with theoretical guarantees to determine whether the agent has a…

In this highly speculative Letter it is argued that, under certain physical conditions, Maxwell's demon might be capable of breaking the second law of thermodynamics, thereby allowing a perpetual motion machine of the second kind, by…

Biological systems often choose actions without an explicit reward signal, a phenomenon known as intrinsic motivation. The computational principles underlying this behavior remain poorly understood. In this study, we investigate an…

The exploration of far-from-equilibrium systems has been at the forefront of nonequilibrium thermodynamics, with a particular focus on understanding the fluctuations and response of thermodynamic systems to external perturbations. In this…

Maxwell's demon is a special case of a feedback controlled system, where information gathered by measurement is utilized by driving a system along a thermodynamic process that depends on the measurement outcome. The demon illustrates that…

Our cognition is structuring the informational layer, consisting of perception, anticipation, and action, and it should also be sustained on a physical basis. In this paper, we aim to explore the relationship between the informational layer…

The relation between the theory of entanglement and thermodynamics is very tight: a thermodynamic theory of quantum entanglement, as well as the establishment of rigorous formal connections between the laws of thermodynamics and the…