English
Related papers

Related papers: Full-Gradient Successor Feature Representations

200 papers

Temporal-difference and Q-learning play a key role in deep reinforcement learning, where they are empowered by expressive nonlinear function approximators such as neural networks. At the core of their empirical successes is the learned…

Machine Learning · Computer Science 2024-04-02 Yufeng Zhang , Qi Cai , Zhuoran Yang , Yongxin Chen , Zhaoran Wang

A key question in Reinforcement Learning is which representation an agent can learn to efficiently reuse knowledge between different tasks. Recently the Successor Representation was shown to have empirical benefits for transferring…

Machine Learning · Computer Science 2018-07-06 Lucas Lehnert , Michael L. Littman

Deep reinforcement learning (DRL) frameworks are increasingly used to solve high-dimensional continuous control tasks in robotics. However, due to the lack of sample efficiency, applying DRL for online learning is still practically…

Robotics · Computer Science 2024-04-30 Yu Tang Liu , Aamir Ahmad

While deep reinforcement learning (RL) has been demonstrated effective in solving complex control tasks, sample efficiency remains a key challenge due to the large amounts of data required for remarkable performance. Existing research…

Machine Learning · Computer Science 2023-10-25 Mingxuan Ye , Yufei Kuang , Jie Wang , Rui Yang , Wengang Zhou , Houqiang Li , Feng Wu

Unlike their conventional use as estimators of probability density functions in reinforcement learning (RL), this paper introduces a novel function-approximation role for Gaussian mixture models (GMMs) as direct surrogates for Q-function…

Machine Learning · Computer Science 2025-12-23 Minh Vu , Konstantinos Slavakis

We propose Fractional Policy Gradients (FPG), a reinforcement learning framework incorporating fractional calculus for long-term temporal modeling in policy optimization. Standard policy gradient approaches face limitations from Markovian…

Machine Learning · Computer Science 2025-07-02 Urvi Pawar , Kunal Telangi

Federated learning (FL) is a paradigm where many clients collaboratively train a model under the coordination of a central server, while keeping the training data locally stored. However, heterogeneous data distributions over different…

Machine Learning · Computer Science 2022-05-27 Yaqi Sun , Shijing Si , Jianzong Wang , Yuhan Dong , Zhitao Zhu , Jing Xiao

In reinforcement learning, temporal difference-based algorithms can be sample-inefficient: for instance, with sparse rewards, no learning occurs until a reward is observed. This can be remedied by learning richer objects, such as a model of…

Machine Learning · Computer Science 2021-01-19 Léonard Blier , Corentin Tallec , Yann Ollivier

Deep Q-Networks (DQNs) estimate future returns by learning from transitions sampled from a replay buffer. However, the target updates in DQN often rely on next states generated by actions from past, potentially suboptimal, policy. As a…

Machine Learning · Computer Science 2025-11-07 Lipeng Zu , Hansong Zhou , Xiaonan Zhang

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

Here we propose using the successor representation (SR) to accelerate learning in a constructive knowledge system based on general value functions (GVFs). In real-world settings like robotics for unstructured and dynamic environments, it is…

Machine Learning · Computer Science 2018-03-28 Craig Sherstan , Marlos C. Machado , Patrick M. Pilarski

Federated learning (FL) enables collaborative model training across multiple parties without sharing raw data, with semi-asynchronous FL (SAFL) emerging as a balanced approach between synchronous and asynchronous FL. However, SAFL faces…

Machine Learning · Computer Science 2025-11-26 Yunbo Li , Jiaping Gui , Zhihang Deng , Fanchao Meng , Yue Wu

We study reinforcement learning (RL) with no-reward demonstrations, a setting in which an RL agent has access to additional data from the interaction of other agents with the same environment. However, it has no access to the rewards or…

Machine Learning · Computer Science 2021-06-11 Angelos Filos , Clare Lyle , Yarin Gal , Sergey Levine , Natasha Jaques , Gregory Farquhar

The forward-backward representation (FB) is a recently proposed framework (Touati et al., 2023; Touati & Ollivier, 2021) to train behavior foundation models (BFMs) that aim at providing zero-shot efficient policies for any new task…

Machine Learning · Computer Science 2024-12-06 Edoardo Cetin , Ahmed Touati , Yann Ollivier

Federated learning (FL) has emerged as a privacy-preserving machine learning approach where multiple parties share gradient information rather than original user data. Recent work has demonstrated that gradient inversion attacks can exploit…

Machine Learning · Computer Science 2024-05-07 Jin Qian , Kaimin Wei , Yongdong Wu , Jilian Zhang , Jipeng Chen , Huan Bao

In Reinforcement Learning (RL), training a policy from scratch with online experiences can be inefficient because of the difficulties in exploration. Recently, offline RL provides a promising solution by giving an initialized offline…

Machine Learning · Computer Science 2024-05-14 Changhong Wang , Xudong Yu , Chenjia Bai , Qiaosheng Zhang , Zhen Wang

Reinforcement learning is essential for neural architecture search and hyperparameter optimization, but the conventional approaches impede widespread use due to prohibitive time and computational costs. Inspired by DeepSeek-V3 multi-token…

Machine Learning · Computer Science 2025-06-19 Zheng Li , Jerry Cheng , Huanying Helen Gu

Real-world visual search systems involve deployments on multiple platforms with different computing and storage resources. Deploying a unified model that suits the minimal-constrain platforms leads to limited accuracy. It is expected to…

Artificial Intelligence · Computer Science 2023-03-24 Shengsen Wu , Yan Bai , Yihang Lou , Xiongkun Linghu , Jianzhong He , Ling-Yu Duan

Recent advancements in semantic communication have primarily focused on image transmission, where neural network-based joint source-channel coding modules play a central role. However, such systems often experience semantic communication…

Signal Processing · Electrical Eng. & Systems 2026-02-20 Yoon Huh , Bumjun Kim , Wan Choi

Spiking Neural Networks (SNNs) offer a biologically plausible framework for energy-efficient neuromorphic computing. However, it is a challenge to train SNNs due to their non-differentiability, efficiently. Existing gradient approximation…

Computer Vision and Pattern Recognition · Computer Science 2025-08-04 Changqing Xu , Ziqiang Yang , Yi Liu , Xinfang Liao , Guiqi Mo , Hao Zeng , Yintang Yang