AI Agent - arXivDaily 专题

1903.09328 2019-03-25 cs.AI 57%

Improving Safety in Reinforcement Learning Using Model-Based Architectures and Human Intervention

Bharat Prakash, Mohit Khatwani, Nicholas Waytowich, Tinoosh Mohsenin

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI

1903.04932 2019-03-13 cs.RO cs.LG 57%

Goal-Directed Behavior under Variational Predictive Coding: Dynamic Organization of Visual Attention and Working Memory

Minju Jung, Takazumi Matsumoto, Jun Tani

专题命中记忆与上下文管理：planning(abstract)；分类 cs.LG

1708.02378 2019-03-13 cs.AI 57%

Investigating Reinforcement Learning Agents for Continuous State Space Environments

David Von Dollen

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI

1803.03146 2019-03-07 q-bio.QM cs.AI stat.ML 57%

SentRNA: Improving computational RNA design by incorporating a prior of human design strategies

Jade Shi, Rhiju Das, Vijay S. Pande

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI

Comments 27 pages (not including Supplementary Information), 9 figures, 7 tables

1810.04329 2019-03-01 cs.DC cs.LG 57%

Task Runtime Prediction in Scientific Workflows Using an Online Incremental Learning Approach

Muhammad H. Hilman, Maria A. Rodriguez, Rajkumar Buyya

专题命中记忆与上下文管理：workflow(abstract)；分类 cs.LG

Comments Accepted for presentation at main conference track of 11th IEEE/ACM International Conference on Utility and Cloud Computing

1812.11202 2019-02-25 cs.LG cs.NE 57%

State representation learning with recurrent capsule networks

Louis Annabi, Michael Garcia Ortiz

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments 4 pages, 4 figures, NIPS Workshop on Modeling the Physical World: Perception, Learning, and Control

1902.06598 2019-02-19 cs.SI cs.CL 57%

Network connectivity dynamics affect the evolution of culturally transmitted variants

José Segovia Martín, Bradley Walker, Nicolas Fay, Monica Tamariz

专题命中记忆与上下文管理：agent(abstract)；分类 cs.CL

Comments Electronic supplementary material and simulation code are available at: https://github.com/jsegoviamartin/network_connectivity_dynamics_model

1902.06178 2019-02-19 cs.LO cs.AI 57%

Iterated Belief Base Revision: A Dynamic Epistemic Logic Approach

Marlo Souza, Álvaro Moreira, Renata Vieira

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI

Comments 8 pages, AAAI2019

1802.07569 2019-02-12 cs.LG q-bio.NC stat.ML 57%

Continual Lifelong Learning with Neural Networks: A Review

German I. Parisi, Ronald Kemker, Jose L. Part, Christopher Kanan, Stefan Wermter

专题命中记忆与上下文管理：autonomous agent(abstract)；分类 cs.LG

1802.03692 2019-01-25 stat.ML cs.LG 57%

Nearly Optimal Adaptive Procedure with Change Detection for Piecewise-Stationary Bandit

Yang Cao, Zheng Wen, Branislav Kveton, Yao Xie

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

1810.00746 2019-01-23 cs.CV cs.LG 57%

Bayesian Prediction of Future Street Scenes using Synthetic Likelihoods

Apratim Bhattacharyya, Mario Fritz, Bernt Schiele

专题命中记忆与上下文管理：autonomous agent(abstract)；分类 cs.LG

Comments To appear in ICLR 2019. arXiv admin note: text overlap with arXiv:1806.06939

1805.10966 2018-12-20 cs.AI 57%

Lifelong Learning of Spatiotemporal Representations with Dual-Memory Recurrent Self-Organization

German I. Parisi, Jun Tani, Cornelius Weber, Stefan Wermter

专题命中记忆与上下文管理：autonomous agent(abstract)；分类 cs.AI

Journal ref Parisi GI, Tani J, Weber C and Wermter S (2018) Lifelong Learning of Spatiotemporal Representations With Dual-Memory Recurrent Self-Organization. Front. Neurorobot. 12:78

1812.04227 2018-12-12 cs.LG stat.ML 57%

Learning What to Remember: Long-term Episodic Memory Networks for Learning from Streaming Data

Hyunwoo Jung, Moonsu Han, Minki Kang, Sungju Hwang

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

1811.02113 2018-12-03 cs.NE cs.LG 57%

On the role of neurogenesis in overcoming catastrophic forgetting

German I. Parisi, Xu Ji, Stefan Wermter

专题命中记忆与上下文管理：autonomous agent(abstract)；分类 cs.LG

Comments Accepted to NIPS'18 Workshop on Continual Learning

1811.07868 2018-11-26 cs.AI 57%

Simulated Autonomous Driving in a Realistic Driving Environment using Deep Reinforcement Learning and a Deterministic Finite State Machine

Patrick Klose, Rudolf Mester

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI

Comments This paper is submitted to Applications of Intelligent Systems (APPIS) 2019 for review

1809.05630 2018-11-16 cs.LG stat.ML 57%

Towards Better Interpretability in Deep Q-Networks

Raghuram Mandyam Annasamy, Katia Sycara

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments Accepted at AAAI-19; (16 pages, 18 figures)

1811.04323 2018-11-14 cs.CV cs.AI 57%

Fully Convolutional Network with Multi-Step Reinforcement Learning for Image Processing

Ryosuke Furuta, Naoto Inoue, Toshihiko Yamasaki

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI

Comments Accepted to AAAI 2019

1811.03830 2018-11-13 cs.CV cs.AI 57%

Image-Level Attentional Context Modeling Using Nested-Graph Neural Networks

Guillaume Jaume, Behzad Bozorgtabar, Hazim Kemal Ekenel, Jean-Philippe Thiran, Maria Gabrani

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI

Comments NIPS 2018, Relational Representation Learning Workshop

1810.11748 2018-10-30 cs.HC cs.LG 57%

DQN-TAMER: Human-in-the-Loop Reinforcement Learning with Intractable Feedback

Riku Arakawa, Sosuke Kobayashi, Yuya Unno, Yuta Tsuboi, Shin-ichi Maeda

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

1810.10358 2018-10-25 cs.CV cs.LG stat.ML 57%

Implicit Modeling with Uncertainty Estimation for Intravoxel Incoherent Motion Imaging

Lin Zhang, Valery Vishnevskiy, Andras Jakab, Orcun Goksel

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

1810.09401 2018-10-23 cs.IR cs.LG stat.ML 57%

Alternating Linear Bandits for Online Matrix-Factorization Recommendation

Hamid Dadkhahi, Sahand Negahban

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

1810.05394 2018-10-15 cs.LG cs.CV cs.RO stat.ML 57%

Sequential Learning of Movement Prediction in Dynamic Environments using LSTM Autoencoder

Meenakshi Sarkar, Debasish Ghose

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments 4 pages

1806.06939 2018-10-01 cs.CV cs.LG 57%

Bayesian Prediction of Future Street Scenes through Importance Sampling based Optimization

Apratim Bhattacharyya, Mario Fritz, Bernt Schiele

专题命中记忆与上下文管理：autonomous agent(abstract)；分类 cs.LG

Comments The objective in (8) allows for trivial solutions e.g. the prior

1809.05872 2018-09-18 cs.LG stat.ML 57%

Inspiration Learning through Preferences

Nir Baram, Shie Mannor

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

1803.00119 2018-07-31 cs.AI cs.RO 57%

Integrating Human-Provided Information Into Belief State Representation Using Dynamic Factorization

Rohan Chitnis, Leslie Pack Kaelbling, Tomás Lozano-Pérez

专题命中记忆与上下文管理：planning(abstract)；分类 cs.AI

Comments IROS 2018 final version

1807.02787 2018-07-10 q-fin.TR cs.LG stat.ML 57%

Financial Trading as a Game: A Deep Reinforcement Learning Approach

Chien Yi Huang

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

1805.11016 2018-06-04 cs.LG stat.ML 57%

Memory Augmented Self-Play

Shagun Sodhani, Vardaan Pahuja

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

1709.04348 2018-05-29 cs.CL 57%

Natural Language Inference over Interaction Space

Yichen Gong, Heng Luo, Jian Zhang

专题命中记忆与上下文管理：agent(abstract)；分类 cs.CL

Comments 15 pages, 2 figures, under review as ICLR proceeding, Published at Sixth International Conference on Learning Representations, ICLR 2018

1805.06020 2018-05-22 cs.AI 57%

Do deep reinforcement learning agents model intentions?

Tambet Matiisen, Aqeel Labash, Daniel Majoral, Jaan Aru, Raul Vicente

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI

1803.00268 2018-04-27 cs.AI cs.RO 57%

Representation Learning in Partially Observable Environments using Sensorimotor Prediction

Thibaut Kulak, Michael Garcia Ortiz

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI

1. 记忆与上下文管理 4786 篇

Improving Safety in Reinforcement Learning Using Model-Based Architectures and Human Intervention

Goal-Directed Behavior under Variational Predictive Coding: Dynamic Organization of Visual Attention and Working Memory

Investigating Reinforcement Learning Agents for Continuous State Space Environments

SentRNA: Improving computational RNA design by incorporating a prior of human design strategies

Task Runtime Prediction in Scientific Workflows Using an Online Incremental Learning Approach

State representation learning with recurrent capsule networks

Network connectivity dynamics affect the evolution of culturally transmitted variants

Iterated Belief Base Revision: A Dynamic Epistemic Logic Approach

Continual Lifelong Learning with Neural Networks: A Review

Nearly Optimal Adaptive Procedure with Change Detection for Piecewise-Stationary Bandit

Bayesian Prediction of Future Street Scenes using Synthetic Likelihoods

Lifelong Learning of Spatiotemporal Representations with Dual-Memory Recurrent Self-Organization

Learning What to Remember: Long-term Episodic Memory Networks for Learning from Streaming Data

On the role of neurogenesis in overcoming catastrophic forgetting

Simulated Autonomous Driving in a Realistic Driving Environment using Deep Reinforcement Learning and a Deterministic Finite State Machine

Towards Better Interpretability in Deep Q-Networks

Fully Convolutional Network with Multi-Step Reinforcement Learning for Image Processing

Image-Level Attentional Context Modeling Using Nested-Graph Neural Networks

DQN-TAMER: Human-in-the-Loop Reinforcement Learning with Intractable Feedback

Implicit Modeling with Uncertainty Estimation for Intravoxel Incoherent Motion Imaging

Alternating Linear Bandits for Online Matrix-Factorization Recommendation

Sequential Learning of Movement Prediction in Dynamic Environments using LSTM Autoencoder

Bayesian Prediction of Future Street Scenes through Importance Sampling based Optimization

Inspiration Learning through Preferences

Integrating Human-Provided Information Into Belief State Representation Using Dynamic Factorization

Financial Trading as a Game: A Deep Reinforcement Learning Approach

Memory Augmented Self-Play

Natural Language Inference over Interaction Space

Do deep reinforcement learning agents model intentions?

Representation Learning in Partially Observable Environments using Sensorimotor Prediction