English
Related papers

Related papers: Combining Behaviors with the Successor Features Ke…

200 papers

Real-world problems often involve complex objective structures that resist distillation into reinforcement learning environments with a single objective. Operation costs must be balanced with multi-dimensional task performance and…

Machine Learning · Computer Science 2024-09-10 Ian Cannon , Washington Garcia , Thomas Gresavage , Joseph Saurine , Ian Leong , Jared Culbertson

Nowadays, cooperative multi-agent systems are used to learn how to achieve goals in large-scale dynamic environments. However, learning in these environments is challenging: from the effect of search space size on learning time to…

Multiagent Systems · Computer Science 2022-01-19 Mahnoosh Mahdavimoghaddam , Amin Nikanjam , Monireh Abdoos

Multitask Learning is a learning paradigm that deals with multiple different tasks in parallel and transfers knowledge among them. XOF, a Learning Classifier System using tree-based programs to encode building blocks (meta-features),…

Neural and Evolutionary Computing · Computer Science 2020-09-14 Trung B. Nguyen , Will N. Browne , Mengjie Zhang

Operating in the real-world often requires agents to learn about a complex environment and apply this understanding to achieve a breadth of goals. This problem, known as goal-conditioned reinforcement learning (GCRL), becomes especially…

Machine Learning · Computer Science 2021-11-19 Christopher Hoang , Sungryull Sohn , Jongwook Choi , Wilka Carvalho , Honglak Lee

Detection transformers have recently shown promising object detection results and attracted increasing attention. However, how to develop effective domain adaptation techniques to improve its cross-domain performance remains unexplored and…

Computer Vision and Pattern Recognition · Computer Science 2022-07-18 Wen Wang , Yang Cao , Jing Zhang , Fengxiang He , Zheng-Jun Zha , Yonggang Wen , Dacheng Tao

In reinforcement learning, universal successor features (SFs) are a way to provide zero-shot adaptation to new tasks at test time: they provide optimal policies for all downstream reward functions lying in the linear span of a set of base…

Machine Learning · Computer Science 2025-02-18 Yann Ollivier

A key question in reinforcement learning is how an intelligent agent can generalize knowledge across different inputs. By generalizing across different inputs, information learned for one input can be immediately reused for improving…

Machine Learning · Computer Science 2020-10-06 Lucas Lehnert , Michael L. Littman

Abstraction is an important aspect of intelligence which enables agents to construct robust representations for effective decision making. In the last decade, deep networks are proven to be effective due to their ability to form…

Robotics · Computer Science 2022-09-28 Alper Ahmetoglu , Emre Ugur , Minoru Asada , Erhan Oztop

Scaling Transformers to ultra-long contexts is bottlenecked by the $O(n^2 d)$ cost of self-attention. Existing methods reduce this cost along the sequence axis through local windows, kernel approximations, or token-level sparsity, but these…

Machine Learning · Computer Science 2026-03-31 Yan Xie , Tiansheng Wen , Tangda Huang , Bo Chen , Chenyu You , Stefanie Jegelka , Yifei Wang

Recent studies in neuroscience suggest that Successor Representation (SR)-based models provide adaptation to changes in the goal locations or reward function faster than model-free algorithms, together with lower computational cost compared…

Neural and Evolutionary Computing · Computer Science 2022-04-04 Parvin Malekzadeh , Mohammad Salimibeni , Ming Hou , Arash Mohammadi , Konstantinos N. Plataniotis

This paper presents a novel framework for continual feature selection (CFS) in data preprocessing, particularly in the context of an open and dynamic environment where unknown classes may emerge. CFS encounters two primary challenges: the…

Machine Learning · Computer Science 2024-03-18 Xuemei Cao , Xin Yang , Shuyin Xia , Guoyin Wang , Tianrui Li

There is an interest in finding energy efficient alternatives to current state of the art neural network training algorithms. Spiking neural network are a promising approach, because they can be simulated energy efficiently on neuromorphic…

Neural and Evolutionary Computing · Computer Science 2024-03-15 Florian Bacho , Dminique Chu

Conventional reinforcement learning (RL) methods can successfully solve a wide range of sequential decision problems. However, learning policies that can generalize predictably across multiple tasks in a setting with non-Markovian reward…

Machine Learning · Computer Science 2024-06-04 Guillermo Infante , David Kuric , Anders Jonsson , Vicenç Gómez , Herke van Hoof

Technology advances in areas such as sensors, IoT, and robotics, enable new collaborative applications (e.g., autonomous devices). A primary requirement for such collaborations is to have a secure system which enables information sharing…

Cryptography and Security · Computer Science 2020-11-04 Amani Abu Jabal , Elisa Bertino , Jorge Lobo , Dinesh Verma , Seraphin Calo , Alessandra Russo

The transfer of a neural network (CNN) trained to recognize objects to the task of scene classification is considered. A Bag-of-Semantics (BoS) representation is first induced, by feeding scene image patches to the object CNN, and…

Computer Vision and Pattern Recognition · Computer Science 2019-05-29 Mandar Dixit , Yunsheng Li , Nuno Vasconcelos

Fast Fourier convolution (FFC) is the recently proposed neural operator showing promising performance in several computer vision problems. The FFC operator allows employing large receptive field operations within early layers of the neural…

Sound · Computer Science 2022-04-08 Ivan Shchekotov , Pavel Andreev , Oleg Ivanov , Aibek Alanov , Dmitry Vetrov

Based on the predictive map theory of spatial learning in animals, this study delves into the dynamics of Successor Feature (SF) and Predecessor Feature (PF) algorithms within noisy environments. Utilizing Q-learning and Q($\lambda$)…

Neural and Evolutionary Computing · Computer Science 2024-02-08 Hyunsu Lee

We describe CFW, a computationally efficient algorithm for collaborative filtering that uses posteriors over weights of evidence. In experiments on real data, we show that this method predicts as well or better than other methods in…

Information Retrieval · Computer Science 2015-05-19 Carl Kadie , Christopher Meek , David Heckerman

Unsupervised domain adaptation (UDA) has attracted considerable attention, which transfers knowledge from a label-rich source domain to a related but unlabeled target domain. Reducing inter-domain differences has always been a crucial…

Computer Vision and Pattern Recognition · Computer Science 2025-02-04 Lianyu Wang , Meng Wang , Daoqiang Zhang , Huazhu Fu

Agents that operate autonomously benefit from lifelong learning capabilities. However, compatible training algorithms must comply with the decentralized nature of these systems, which imposes constraints on both the parameter counts and the…

Machine Learning · Computer Science 2025-03-28 Xing Chen , Dongshu Liu , Jeremie Laydevant , Julie Grollier