English
Related papers

Related papers: Learning by training: emergent return-point memory…

200 papers

An adaptive agent predicting the future state of an environment must weigh trust in new observations against prior experiences. In this light, we propose a view of the adaptive immune system as a dynamic Bayesian machinery that updates its…

Populations and Evolution · Quantitative Biology 2019-05-14 Andreas Mayer , Vijay Balasubramanian , Aleksandra M. Walczak , Thierry Mora

In meta-reinforcement learning, an agent is trained in multiple different environments and attempts to learn a meta-policy that can efficiently adapt to a new environment. This paper presents RAMP, a Reinforcement learning Agent using Model…

Machine Learning · Computer Science 2022-10-28 Gabriel Hartmann , Amos Azaria

The exploration of whether agents can align with their environment without relying on human-labeled data presents an intriguing research topic. Drawing inspiration from the alignment process observed in intelligent organisms, where…

Computation and Language · Computer Science 2024-03-06 Bo Wang , Tianxiang Sun , Hang Yan , Siyin Wang , Qingyuan Cheng , Xipeng Qiu

By training linear physical networks to learn linear transformations, we discern how their physical properties evolve due to weight update rules. Our findings highlight a striking similarity between the learning behaviors of such networks…

Disordered Systems and Neural Networks · Physics 2023-11-01 Vidyesh Rao Anisetti , Ananth Kandala , J. M. Schwarz

Emergent learning transforms a disordered optical medium into a photonic device capable of storage, recognition, and classification of arbitrary memory patterns. First, we show that the intensity at the output of a multiply scattering…

Real-world artificial intelligence (AI) systems are increasingly required to operate autonomously in dynamic, uncertain, and continuously changing environments. However, most existing AI models rely on predefined objectives, static training…

Artificial Intelligence · Computer Science 2025-11-04 Hong Su

Natural spatiotemporal processes can be highly non-stationary in many ways, e.g. the low-level non-stationarity such as spatial correlations or temporal dependencies of local pixel values; and the high-level variations such as the…

Machine Learning · Computer Science 2019-04-23 Yunbo Wang , Jianjin Zhang , Hongyu Zhu , Mingsheng Long , Jianmin Wang , Philip S Yu

In order for robots and other artificial agents to efficiently learn to perform useful tasks defined by an end user, they must understand not only the goals of those tasks, but also the structure and dynamics of that user's environment.…

Artificial Intelligence · Computer Science 2019-07-22 Robert Loftin , Bei Peng , Matthew E. Taylor , Michael L. Littman , David L. Roberts

Reprogrammable mechanical metamaterials, composed of a lattice of discretely adaptive elements, are emerging as a promising platform for mechanical intelligence. To operate in unknown environments, such structures must go beyond passive…

Deep reinforcement learning is used in various domains, but usually under the assumption that the environment has stationary conditions like transitions and state distributions. When this assumption is not met, performance suffers. For this…

Machine Learning · Computer Science 2024-05-24 Zihe Liu , Jie Lu , Guangquan Zhang , Junyu Xuan

This work focuses on the training dynamics of one associative memory module storing outer products of token embeddings. We reduce this problem to the study of a system of particles, which interact according to properties of the data…

Machine Learning · Computer Science 2024-03-01 Vivien Cabannes , Berfin Simsek , Alberto Bietti

Autonomous AI agents operating in dynamic environments face a persistent challenge: acquiring new capabilities without erasing prior knowledge. We present Adaptive Memory Crystallization (AMC), a memory architecture for progressive…

Machine Learning · Computer Science 2026-04-16 Rajat Khanda , Mohammad Baqar Sambuddha Chakrabarti , Satyasaran Changdar

Learning a reward function from demonstrations suffers from low sample-efficiency. Even with abundant data, current inverse reinforcement learning methods that focus on learning from a single environment can fail to handle slight changes in…

Machine Learning · Computer Science 2024-05-15 Thomas Kleine Buening , Victor Villin , Christos Dimitrakakis

Learning-based control methods typically assume stationary system dynamics, an assumption often violated in real-world systems due to drift, wear, or changing operating conditions. We study reinforcement learning for control under…

Machine Learning · Computer Science 2026-04-03 Klemens Iten , Bruce Lee , Chenhao Li , Lenart Treven , Andreas Krause , Bhavya Sukhija

Adapting a Reinforcement Learning (RL) agent to an unseen environment is a difficult task due to typical over-fitting on the training environment. RL agents are often capable of solving environments very close to the trained environment,…

Artificial Intelligence · Computer Science 2022-07-04 Olivier Moulin , Vincent Francois-Lavet , Paul Elbers , Mark Hoogendoorn

Organisms constantly pivot between tasks such as evading predators, foraging, traversing rugged terrain, and socializing, often within milliseconds. Remarkably, they preserve knowledge of once-learned environments sans catastrophic…

Machine Learning · Computer Science 2025-12-02 Susmit Agrawal , Krishn Vishwas Kher , Saksham Mittal , Swarnim Maheshwari , Vineeth N. Balasubramanian

The utility of learning a dynamics/world model of the environment in reinforcement learning has been shown in a many ways. When using neural networks, however, these models suffer catastrophic forgetting when learned in a lifelong or…

Machine Learning · Computer Science 2019-06-12 Nicholas Ketz , Soheil Kolouri , Praveen Pilly

Biological evolution of a population is governed by the fitness landscape, which is a map from genotype to fitness. However, a fitness landscape depends on the organisms environment, and evolution in changing environments is still poorly…

Populations and Evolution · Quantitative Biology 2022-09-26 Suman G Das , Joachim Krug , Muhittin Mungan

Cyclically sheared jammed packings form memories of the shear amplitude at which they were trained by falling into periodic orbits where each particle returns to the identical position in subsequent cycles. While simple models that treat…

Soft Condensed Matter · Physics 2023-08-31 Chloe W. Lindeman , Sidney R. Nagel

Multi-agent reinforcement learning (MARL) extends (single-agent) reinforcement learning (RL) by introducing additional agents and (potentially) partial observability of the environment. Consequently, algorithms for solving MARL problems…

Multiagent Systems · Computer Science 2019-09-12 Yilun Zhou , Derrik E. Asher , Nicholas R. Waytowich , Julie A. Shah