Related papers: Beyond Sliding Windows: Learning to Manage Memory …

Learning shared structure across environments facilitates rapid learning and adaptive behavior in neural systems. This has been widely demonstrated and applied in machine learning to train models that are capable of generalizing to novel…

Learning models of artificial intelligence can nowadays perform very well on a large variety of tasks. However, in practice different task environments are best handled by different learning models, rather than a single, universal,…

Experience-driven learning has emerged as a promising paradigm for enabling agents to improve from interaction trajectories by accumulating and reusing past experience. However, existing approaches are predominantly developed in textual…

We present an approach for agents to learn representations of a global map from sensor data, to aid their exploration in new environments. To achieve this, we embed procedures mimicking that of traditional Simultaneous Localization and…

Emerging computing architectures such as near-memory computing (NMC) promise improved performance for applications by reducing the data movement between CPU and memory. However, detecting such applications is not a trivial task. In this…

Tasks in which rewards depend upon past information not available in the current observation set can only be solved by agents that are equipped with short-term memory. Usual choices for memory modules include trainable recurrent hidden…

An emerging paradigm in vision-and-language navigation (VLN) is the use of history-aware multi-modal transformer models. Given a language instruction, these models process observation and navigation history to predict the most appropriate…

To generalize across tasks, an agent should acquire knowledge from past tasks that facilitate adaptation and exploration in future tasks. We focus on the problem of in-context adaptation and exploration, where an agent only relies on…

Transformer-based LLMs have achieved exceptional performance across a wide range of NLP tasks. However, the standard self-attention mechanism suffers from quadratic time complexity and linearly increased cache size. Sliding window attention…

The proof that Large Language Models (LLMs) augmented with external read-write memory constitute a computationally universal system has established the theoretical foundation for general-purpose agents. However, existing implementations…

Reinforcement learning agents deployed in the real world often have to cope with partially observable environments. Therefore, most agents employ memory mechanisms to approximate the state of the environment. Recently, there have been…

We consider the problem of optimizing time averages in systems with independent and identically distributed behavior over renewal frames. This includes scheduling and task processing to maximize utility in stochastic networks with variable…

An important aspect of intelligence is the ability to adapt to a novel task without any direct experience (zero-shot), based on its relationship to previous tasks. Humans can exhibit this cognitive flexibility. By contrast, models that…

Computational agents support humans in many areas of life and are therefore found in heterogeneous contexts. This means they operate in rapidly changing environments and can be confronted with huge state and action spaces. In order to…

Non-Markovian dynamics are ubiquitous across physics, biology, and engineering. Yet our understanding of non-Markovian processes significantly lags that of simpler Markovian processes, due largely to a lack of tractable models. In this…

Markov Decision Process (MDP) presents a mathematical framework to formulate the learning processes of agents in reinforcement learning. MDP is limited by the Markovian assumption that a reward only depends on the immediate state and…

We tackle the problem of policy learning from expert demonstrations without a reward function. A central challenge in this space is that these policies fail upon deployment due to issues of distributional shift, environment stochasticity,…

In this report we review memory-based meta-learning as a tool for building sample-efficient strategies that learn from past experience to adapt to any task within a target class. Our goal is to equip the reader with the conceptual…

Decomposing knowledge into interchangeable pieces promises a generalization advantage when there are changes in distribution. A learning agent interacting with its environment is likely to be faced with situations requiring novel…

This paper introduces a novel approach to enhance the capabilities of Large Language Models (LLMs) in processing and understanding extensive text sequences, a critical aspect in applications requiring deep comprehension and synthesis of…