Related papers: Learning a world model and planning with a self-or…
Despite the recent progress in deep learning and reinforcement learning, transfer and generalization of skills learned on specific tasks is very limited compared to human (or animal) intelligence. The lifelong, incremental building of…
Active systems across scales, ranging from molecular machines to human crowds, are usually modeled as assemblies of self-propelled particles driven by internally generated forces. However, these models often assume memoryless dynamics and…
We propose a self-organizing memory architecture for perceptual experience, capable of supporting autonomous learning and goal-directed problem solving in the absence of any prior information about the agent's environment. The architecture…
To make progress in science, we often build abstract representations of physical systems that meaningfully encode information about the systems. The representations learnt by most current machine learning techniques reflect statistical…
Consider the finite state graph that results from a simple, discrete, dynamical system in which an agent moves in a rectangular grid picking up and dropping packages. Can the state variables of the problem, namely, the agent location and…
This work introduces a general multi-level model for self-adaptive systems. A self-adaptive system is seen as composed by two levels: the lower level describing the actual behaviour of the system and the upper level accounting for the…
A world model matters to an agent only through the state it constructs. That state must preserve some information, discard other information, and support some future function: prediction, control, planning, memory, grounding, or…
Decision analysis deals with modeling and enhancing decision processes. A principal challenge in improving behavior is in obtaining a transparent description of existing behavior in the first place. In this paper, we develop an expressive,…
To interact with humans and act in the world, agents need to understand the range of language that people use and relate it to the visual world. While current agents can learn to execute simple language instructions, we aim to build agents…
LLMs are trained once, then deployed into a world that never stops changing. External memory compensates for this, but most systems manage it explicitly rather than letting it adapt on its own. Biological memory works differently: coupled…
Planning - the ability to analyze the structure of a problem in the large and decompose it into interrelated subproblems - is a hallmark of human intelligence. While deep reinforcement learning (RL) has shown great promise for solving…
A world model is essential for an agent to predict the future and plan in domains such as autonomous driving and robotics. To achieve this, recent advancements have focused on video generation, which has gained significant attention due to…
A key challenge for autonomous driving is safe trajectory planning in cluttered, urban environments with dynamic obstacles, such as pedestrians, bicyclists, and other vehicles. A reliable prediction of the future environment, including the…
In order to understand the development of common orientation of opinions in the modern world we propose a model of a society described as a large collection of agents that exchange their expressed opinions under the influence of their…
A new interpretable experiential learning model based on state history and global feedback is presented. It is capable of learning a behavioral model represented by a transition graph between sets of states, with transitions attributed with…
A cognitive map is an internal model which encodes the abstract relationships among entities in the world, giving humans and animals the flexibility to adapt to new situations, with a strong out-of-distribution (OOD) generalization that…
We introduce a new model, the Recurrent Entity Network (EntNet). It is equipped with a dynamic long-term memory which allows it to maintain and update a representation of the state of the world as it receives new data. For language…
Every day, humans perceive objects and communicate these perceptions through various channels. In this paper, we present a computational model designed to track and simulate the perception of objects, as well as their representations as…
Can neural networks learn goal-directed behaviour using similar strategies to the brain, by combining the relationships between the current state of the organism and the consequences of future actions? Recent work has shown that recurrent…
We introduce a model that learns active learning algorithms via metalearning. For a distribution of related tasks, our model jointly learns: a data representation, an item selection heuristic, and a method for constructing prediction…