Search

Topics

Environment198 papers Environmental Uncertainty27 papers Urban Environments182 papers Unknown Environments112 papers Real-World Environments69 papers 3D Environments28 papers Indoor Environments28 papers Railway Environments17 papers Harbor Environments14 papers Agentic Control87 papers Sea-Surface Temperature Data45 papers Ocean43 papers

Papers 6,871–6,900 of 6,967

TERC: A Transfer Entropy Redundancy Criterion for State Variable Selection in Reinforcement Learning
Jan 21, 2024Charles Westphal, Stephen Hailes, Mirco MusolesiEntropy Regularized Reinforcement Learning Proximal Policy Optimization
UCL Centre for Artificial Intelligence Department of Computer Science University College London Gower Street, London WC1E 6BT, United Kingdom · Department of Computer Science University College London Gower Street, London WC1E 6BT, United Kingdom · Department of Computer Science and Engineering University of Bologna Viale Del Risorgimento 2, 40136 Bologna, Italy
Bridging Language and Action: A Survey of Language-Conditioned Robot Manipulation
Dec 17, 2023Xiangtong Yao, Hongkuan Zhou, Oier Mees +12Generalizable Robotic Manipulations Language-Conditioning Space Policy
Technical University of Munich, Munich, Germany · Corporate Research, Robert Bosch GmbH, Renningen, Germany · Institute for Artificial Intelligence, University of Stuttgart, Stuttgart, Germany +10
Uncertainty Quantification in Machine Learning for Biosignal Applications -- A Review
Nov 15, 2023Ivo Pascal de Jong, Andreea Ioana Sburlea, Matias Valdenegro-ToroMultimodal Physiological Signals Reliable Uncertainty Quantification
Department of Artificial Intelligence, Bernoulli Institute, University of Groningen, Groningen, The Netherlands
DIRA-SS:Dynamic Domain Incremental Regularised Adaptation -- Self-Supervised
Nov 13, 2023Abanoub Ghobrial, Kerstin EderDomain Adaptation Self-Supervised
University of Bristol, Bristol, UK
Causal Discovery in Mixtures of Populations
Nov 13, 2023Bijan Mazaheri, Spencer Gordon, Yuval Rabani +1Causal Foundation Models Structural Equation Models
Thayer School of Engineering, Dartmouth College, Hanover, New Hampshire, USA · Fragment Data Technologies, San Francisco, California, USA · Department of Computer Science, Hebrew Univeristy of Jerusalem, Jerusalem, Israel +1
Data Market Design through Deep Learning
Oct 31, 2023Sai Srivatsa Ravindranath, Yanchen Jiang, David C. ParkesBayesian Experimental Design First-Price Auctions
Harvard John A. Paulson School of Engineering and Applied Sciences
UWA360CAM: A 360 $^{\circ}$ 24/7 Real-Time Streaming Camera System for Underwater Applications
Sep 22, 2023Quan-Dung Pham, Yipeng Zhu, Tan-Sang Ha +3Underwater Image Enhancement Onboard Robot Cameras
Hong Kong University of Science and Technology, Hong Kong SAR. · Trinity College Dublin, Ireland.
ETHER: Aligning Emergent Communication for Hindsight Experience Replay
Jul 28, 2023Kevin Yandoka Denamganaï, Daniel Hernandez, Ozan Vardal +2Goal-Conditioned Reinforcement Learning Reinforcement Learning From Human Feedback
Department of Computer Science University of York York, UK
Calibrated Stackelberg Games: Learning Optimal Commitments Against Calibrated Agents
Jun 5, 2023Nika Haghtalab, Chara Podimata, Kunhe YangMulticalibration and Calibration
University of California, Berkeley · Massachusetts Institute of Technology
Context-Aware System Synthesis, Task Assignment, and Routing
Jun 14, 2017Jason Ziglar, Ryan Williams, Alfred WicksPatient-To-Room Assignment Problem Humanoid Robotics
RoMu4o: A Robotic Manipulation Unit For Orchard Operations Automating Proximal Hyperspectral Leaf Sensing
Date pendingMehrad Mortazavi, David J. Cappelleri, Reza EhsaniAgricultural Robots Robotic Perception
Department of Mechanical Engineering, University of California, Merced, CA, 95343, USA · School of Mechanical Engineering and Weldon School of Biomedical Engineering (By Courtesy), Purdue University, West Lafayette, IN USA 47907
Safe Learning Under Irreversible Dynamics via Asking for Help
Date pendingBenjamin Plaut, Juan Liévano-Karim, Hanlin Zhu +1Markov Decision Processes Near-Optimal Regret Guarantees
Division of Computer Science University of California Berkeley, CA 94720-1776, USA
FLOAT Drone: A Fully-actuated Coaxial Aerial Robot for Close-Proximity Operations
Date pendingJunxiao Lin, Shuhang Ji, Yuze Wu +3Aerial Robots Drone
State Key Laboratory of Industrial Control Technology, Institute of Cyber-Systems and Control, Zhejiang University, Hangzhou, 310027, China
LLM-BabyBench: Can Language Models Plan in Worlds They Can Simulate?
Date pendingIdriss Malek, Omar Choukrani, Daniil Orel +5Large Language Model Planning
Discovering Temporal Structure: An Overview of Hierarchical Reinforcement Learning
Date pendingMartin Klissarov, Akhil Bagaria, Ziyan Luo +3Hierarchical Reinforcement Learning Hierarchical
Mila, McGill University · Amazon · Amii, University of Alberta Canada CIFAR AI Chair
Periodic robust robotic rock chop via virtual model control
Date pendingYi Zhang, Fumiya Iida, Fulvio Forni
University of Cambridge, United Kingdom · University of Tokyo, Japan
Dream4D: Lifting Camera-Controlled I2V towards Spatiotemporally Consistent 4D Generation
Date pendingXiaoyan Liu, Kangrui Li, Jiaxin Liu +24D Generation 4D Reconstruction
The Chinese University of Hong Kong · The Hong Kong Polytechnic University · The University of New South Wales +1
MIMIC-D: Multi-modal Imitation for MultI-agent Coordination with Decentralized Diffusion Policies
Date pendingDayi Dong, Maulik Bhatt, Seoyeon Choi +1Multi-Agent Coordination Multi-Robot Systems
Department of Mechanical Engineering, University of California Berkeley, Berkeley, CA 94709, USA
BiHDTrans: binary hyperdimensional transformer for efficient multivariate time series classification
Date pendingJingtao Zhang, Yi Liu, Qi Shen +1Hybrid Transformer Time-Series Classification
School of Biomedical Engineering, Shenzhen Campus of Sun Yat-sen University · College of Medicine and Biological Information Engineering, Northeastern University
4D-RaDiff: Latent Point Diffusion for 4D Radar Point Cloud Generation
Date pendingJimmie Kwok, Holger Caesar, Andras PalffyLight Detection And Ranging Point Clouds Radar
Delft University of Technology, Netherlands · Perciv AI, Netherlands
AnyView: Synthesizing Any Novel View in Dynamic Scenes
Date pendingBasile Van Hoorick, Dian Chen, Shun Iwase +7Controllable Video Generation Novel View Synthesis
Toyota Research Institute, CA, USA · Amazon Web Services, CA, USA
The Vienna 4G/5G Drive-Test Dataset
Date pendingWilfried Wiedner, Lukas Eller, Mariam Mussbah +4Mobile Networks Naturalistic Driving Data
Institute of Telecommunications, TU Wien, Gusshausstraße 25, 1040 Vienna, Austria · Christian Doppler Laboratory for Digital Twin assisted AI for sustainable Radio Access Networks, TU Wien
Rhythm: Learning Interactive Whole-Body Control for Dual Humanoids
Date pendingHongjin Chen, Wei Zhang, Pengfei Li +10Task-Centric Hybrid Whole-Body Controller Humanoid
Fudan University · TARS Robotics · Tsinghua University +3
CMoE: Contrastive Mixture of Experts for Motion Control and Terrain Adaptation of Humanoid Robots
Date pendingShihao Ma, Hongjin Chen, Zijun Xu +6Long-Tail Humanoid Whole-Body Control Terrain
College of Intelligent Robotics and Advanced Manufacturing, Fudan University, Shanghai, China, 200433
OA-NBV: Occlusion-Aware Next-Best-View Planning for Human-Centered Active Perception on Mobile Robots
Date pendingBoxun Hu, Chang Chang, Jiawei Ge +4Diverse Occlusion-And-Revelation Scenarios Robotics
Department of Electrical and Computer Engineering, Johns Hopkins University, Baltimore, MD 21218, USA · Department of Mechanical Engineering, Johns Hopkins University, Baltimore, MD 21218, USA · Laboratory for Computational Sensing and Robotics, Johns Hopkins University, Baltimore, MD 21218, USA +1
TRUST-SQL: Tool-Integrated Multi-Turn Reinforcement Learning for Text-to-SQL over Unknown Schemas
Date pendingAi Jian, Xiaoyun Zhang, Eryu Guo +6Text-To-Sql Schema
Beijing University of Posts and Telecommunications, Beijing, China · State Key Lab of Processors, Institute of Computing Technology, CAS · University of Chinese Academy of Sciences +1
LLMAR: A Tuning-Free Recommendation Framework for Sparse and Text-Rich Industrial Domains
Date pendingRyogo Hishikawa, Ichiro Kataoka, Shinya YudaCollaborative Filtering Recommendation
Hitachi, Ltd. Research and Development Group Hitachi, Ibaraki, Japan · Hitachi Power Solutions Co., Ltd. Hitachi, Ibaraki, Japan
Dont Just Teach, Explain! A Gamified 20Q Recommender for Cybersecurity Education
Date pendingMary Nusrat, Sarfuddin Bhuiyan, Gahangir HossainOnline Learning Explainable Artificial Intelligence
Information Science, University of North Texas, Denton, TX, USA · Mechanical Engineering, Bangladesh University of Eng. and Tech., BUET, Dhaka, Bangladesh
Joint Architecture-Token-Bitwidth Multi-Axis Optimization of Vision Transformers for Semiconductor IC Packaging
Date pendingPhat Nguyen, Xue Geng, Kaixin Xu +3Vision Transformer Sparse Deep Neural Network Accelerators
Singapore University of Technology and Design (SUTD) · Agency for Science, Technology, and Research (A*STAR)
Capable but Careless: Do Computer-Use Agents Follow Contextual Integrity?
Date pendingAnmol Goel, Iryna GurevychComputer-Use Agents Opti-Agent-Bench
Ubiquitous Knowledge Processing Lab (UKP Lab), Department of Computer Science, TU Darmstadt and National Research Center for Applied Cybersecurity ATHENE

Jan 21, 2024, cs.LGJ/K move · Enter open · S save

TERC: A Transfer Entropy Redundancy Criterion for State Variable Selection in Reinforcement Learning

Charles Westphal, Stephen Hailes, Mirco Musolesi

UCL Centre for Artificial Intelligence Department of Computer Science University College London Gower Street, London WC1E 6BT, United Kingdom · Department of Computer Science University College London Gower Street, London WC1E 6BT, United Kingdom · Department of Computer Science and Engineering University of Bologna Viale Del Risorgimento 2, 40136 Bologna, Italy

Entropy Regularized Reinforcement Learning Proximal Policy Optimization Efficient Inference

Open paper AskPDF arXiv

Identifying the most suitable variables to represent the state is a fundamental challenge in Reinforcement Learning (RL). These variables must efficiently capture the information necessary for making optimal decisions. In order to address this problem, in this paper, we introduce the Transfer Entropy Redundancy Criterion (TERC), an information-theoretic criterion, which determines if there is entropy transferred from observable state variables to actions during training. We define an algorithm based on TERC that provably excludes variables from the observable state that do not affect the agent's policy during learning. This yields compact state representations that reduce inference time by up to 2.6 times. Our approach is policy-dependent, making it agnostic to the underlying learning algorithm. The efficiency gains we demonstrate arise at retraining and inference time on the reduced state. Our method improves both retraining and inference efficiency. We demonstrate its effectiveness across three distinct algorithm classes, namely tabular Q-learning, Actor-Critic, and Proximal Policy Optimization (PPO), evaluated in a range of environments. Furthermore, to highlight the differences between the proposed methodology and the current state-of-the-art feature selection approaches, we present a series of controlled experiments on synthetic data, before generalizing to real-world decision-making tasks. We also introduce a representation of the problem that compactly captures the transfer of information from observable state variables to actions as Bayesian networks.