AI Agent - arXivDaily 专题

2206.13960 2022-06-29 cs.LG cs.AI stat.ML 62%

Dynamic Memory for Interpretable Sequential Optimisation

Srivas Chennu, Andrew Maher, Jamie Martin, Subash Prabanantham

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

Comments 2nd International Workshop on Online and Adaptive Recommender Systems, 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2022, Washington DC

2206.11733 2022-06-24 cs.LG cs.AI cs.RO 62%

Walk the Random Walk: Learning to Discover and Reach Goals Without Supervision

Lina Mezghani, Sainbayar Sukhbaatar, Piotr Bojanowski, Karteek Alahari

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

2206.11708 2022-06-24 cs.LG cs.AI 62%

Reinforcement Learning under Partial Observability Guided by Learned Environment Models

Edi Muskardin, Martin Tappler, Bernhard K. Aichernig, Ingo Pill

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

2206.06614 2022-06-15 cs.LG cs.AI 62%

Transformers are Meta-Reinforcement Learners

Luckeciano C. Melo

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

Comments Published at the International Conference on Machine Learning (ICML) 2022

2111.03917 2022-06-14 cs.LG cs.AI 62%

Optimal and Efficient Dynamic Regret Algorithms for Non-Stationary Dueling Bandits

Aadirupa Saha, Shubham Gupta

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

Comments Accepted to International Conference on Machine Learning (ICML), 2022 [both authors contributed equally]

2203.04297 2022-06-02 cs.LG cs.AI 62%

Rényi State Entropy for Exploration Acceleration in Reinforcement Learning

Mingqi Yuan, Man-on Pun, Dong Wang

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

Comments 10 pages, 6 figures. arXiv admin note: substantial text overlap with arXiv:2203.02298

2205.15400 2022-06-01 cs.LG cs.AI 62%

Designing Rewards for Fast Learning

Henry Sowerby, Zhiyuan Zhou, Michael L. Littman

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

Comments To appear at the 5th Multidisciplinary Conference on Reinforcement Learning and Decision Making (RLDM2022)

2205.07959 2022-05-18 cs.LG cs.AI cs.CV 62%

Deep Apprenticeship Learning for Playing Games

Dejan Markovikj

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

Comments A dissertation submitted in partial fulfillment of the requirements for the degree of Master of Science in Computer Science at University of Oxford

2205.05212 2022-05-12 cs.LG cs.AI cs.RO 62%

A State-Distribution Matching Approach to Non-Episodic Reinforcement Learning

Archit Sharma, Rehaan Ahmad, Chelsea Finn

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

1910.13213 2022-05-03 cs.AI cs.LG 62%

Overcoming Catastrophic Interference in Online Reinforcement Learning with Dynamic Self-Organizing Maps

Yat Long Lo, Sina Ghiassian

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

Comments 9 Pages, 7 Figures, NeurIPS Workshop on Biological and Artificial Reinforcement Learning, 2019

Journal ref Biological and Artificial RL Workshop at NeurIPS 2019

1908.01478 2022-04-29 cs.NE cs.AI cs.LG 62%

Reusability and Transferability of Macro Actions for Reinforcement Learning

Yi-Hsiang Chang, Kuan-Yu Chang, Henry Kuo, Chun-Yi Lee

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

2204.12193 2022-04-27 cs.CV cs.AI cs.LG 62%

Stochastic Coherence Over Attention Trajectory For Continuous Learning In Video Streams

Matteo Tiezzi, Simone Marullo, Lapo Faggi, Enrico Meloni, Alessandro Betti, Stefano Melacci

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

Comments Accepted for publication in the 31st International Joint Conference on Artificial Intelligence (IJCAI-ECAI 2022)

2109.07259 2022-04-15 nlin.AO cs.AI cs.LG cs.MA physics.soc-ph 62%

Modeling the effects of environmental and perceptual uncertainty using deterministic reinforcement learning dynamics with partial observability

Wolfram Barfuss, Richard P. Mann

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

Comments 15 pages, 8 figures

Journal ref Wolfram Barfuss and Richard P. Mann (2022) Phys. Rev. E 105, 034409

2203.16311 2022-04-14 cs.LG cs.AI 62%

When to Go, and When to Explore: The Benefit of Post-Exploration in Intrinsic Motivation

Zhao Yang, Thomas M. Moerland, Mike Preuss, Aske Plaat

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

2204.04285 2022-04-12 cs.CV cs.AI cs.LG 62%

On Improving Cross-dataset Generalization of Deepfake Detectors

Aakash Varma Nadimpalli, Ajita Rattani

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

Comments 2022 Conference on Computer Vision and Pattern Recognition Workshops | New Orleans, Louisiana

2204.03525 2022-04-08 cs.LG cs.AI 62%

Temporal Alignment for History Representation in Reinforcement Learning

Aleksandr Ermolov, Enver Sangineto, Nicu Sebe

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

Comments ICPR 2022

2203.14708 2022-03-29 cs.CV cs.AI cs.LG cs.RO 62%

Object Memory Transformer for Object Goal Navigation

Rui Fukushima, Kei Ota, Asako Kanezaki, Yoko Sasaki, Yusuke Yoshiyasu

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

Comments 7 pages, 3 figures, Accepted at ICRA 2022

2203.10050 2022-03-21 cs.LG cs.AI 62%

SURF: Semi-supervised Reward Learning with Data Augmentation for Feedback-efficient Preference-based Reinforcement Learning

Jongjin Park, Younggyo Seo, Jinwoo Shin, Honglak Lee, Pieter Abbeel, Kimin Lee

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

Comments Accepted to ICLR 2022

2106.12534 2022-03-16 cs.RO cs.AI cs.CV cs.LG 62%

Coarse-to-Fine Q-attention: Efficient Learning for Visual Robotic Manipulation via Discretisation

Stephen James, Kentaro Wada, Tristan Laidlow, Andrew J. Davison

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

Comments Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2022). Videos and code: https://sites.google.com/view/c2f-q-attention

2106.02940 2022-03-16 cs.LG cs.AI 62%

Same State, Different Task: Continual Reinforcement Learning without Interference

Samuel Kessler, Jack Parker-Holder, Philip Ball, Stefan Zohren, Stephen J. Roberts

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

Comments Accepted as an oral at AAAI 2022. 17 pages and 12 figures

2203.02985 2022-03-08 cs.CV cs.AI cs.CL 62%

Dynamic Key-value Memory Enhanced Multi-step Graph Reasoning for Knowledge-based Visual Question Answering

Mingxiao Li, Marie-Francine Moens

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

2203.01465 2022-03-04 cs.LG cs.AI cs.NE 62%

Deep Q-network using reservoir computing with multi-layered readout

Toshitaka Matsuki

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

Comments 17 pages, 9figures

2110.09461 2022-02-25 cs.AI cs.LG 62%

In a Nutshell, the Human Asked for This: Latent Goals for Following Temporal Specifications

Borja G. León, Murray Shanahan, Francesco Belardinelli

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

Journal ref Proceedings of the International Conference of Learning Representations (2022)

2202.07414 2022-02-16 cs.AI cs.LG 62%

Interpretable Reinforcement Learning with Multilevel Subgoal Discovery

Alexander Demin, Denis Ponomaryov

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

2106.06091 2022-02-14 cs.LG cs.AI 62%

DECORE: Deep Compression with Reinforcement Learning

Manoj Alwani, Yang Wang, Vashisht Madhavan

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

2202.03983 2022-02-09 cs.LG cs.AI 62%

Provable Reinforcement Learning with a Short-Term Memory

Yonathan Efroni, Chi Jin, Akshay Krishnamurthy, Sobhan Miryoosefi

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

2202.02790 2022-02-08 cs.LG cs.AI 62%

Learning Synthetic Environments and Reward Networks for Reinforcement Learning

Fabio Ferreira, Thomas Nierhoff, Andreas Saelinger, Frank Hutter

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

Journal ref International Conference on Learning Representations (ICLR 2022)

2110.03743 2022-02-01 cs.LG cs.AI cs.IT math.IT 62%

Reinforcement Learning in Reward-Mixing MDPs

Jeongyeol Kwon, Yonathan Efroni, Constantine Caramanis, Shie Mannor

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

Comments NeurIPS 2021; fixed typo

2106.03926 2022-02-01 cs.AI cs.LG 62%

Reconciling Rewards with Predictive State Representations

Andrea Baisero, Christopher Amato

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

Comments IJCAI 2021

Journal ref Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence (2021) Pages 2170-2176

2102.05599 2022-01-19 cs.LG cs.AI 62%

Improving Model-Based Reinforcement Learning with Internal State Representations through Self-Supervision

Julien Scholz, Cornelius Weber, Muhammad Burhan Hafez, Stefan Wermter

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

Journal ref Proc. Intl. Joint Conf. Neural Networks (IJCNN), 2021, forthcoming

1. 记忆与上下文管理 4786 篇

Dynamic Memory for Interpretable Sequential Optimisation

Walk the Random Walk: Learning to Discover and Reach Goals Without Supervision

Reinforcement Learning under Partial Observability Guided by Learned Environment Models

Transformers are Meta-Reinforcement Learners

Optimal and Efficient Dynamic Regret Algorithms for Non-Stationary Dueling Bandits

Rényi State Entropy for Exploration Acceleration in Reinforcement Learning

Designing Rewards for Fast Learning

Deep Apprenticeship Learning for Playing Games

A State-Distribution Matching Approach to Non-Episodic Reinforcement Learning

Overcoming Catastrophic Interference in Online Reinforcement Learning with Dynamic Self-Organizing Maps

Reusability and Transferability of Macro Actions for Reinforcement Learning

Stochastic Coherence Over Attention Trajectory For Continuous Learning In Video Streams

Modeling the effects of environmental and perceptual uncertainty using deterministic reinforcement learning dynamics with partial observability

When to Go, and When to Explore: The Benefit of Post-Exploration in Intrinsic Motivation

On Improving Cross-dataset Generalization of Deepfake Detectors

Temporal Alignment for History Representation in Reinforcement Learning

Object Memory Transformer for Object Goal Navigation

SURF: Semi-supervised Reward Learning with Data Augmentation for Feedback-efficient Preference-based Reinforcement Learning

Coarse-to-Fine Q-attention: Efficient Learning for Visual Robotic Manipulation via Discretisation

Same State, Different Task: Continual Reinforcement Learning without Interference

Dynamic Key-value Memory Enhanced Multi-step Graph Reasoning for Knowledge-based Visual Question Answering

Deep Q-network using reservoir computing with multi-layered readout

In a Nutshell, the Human Asked for This: Latent Goals for Following Temporal Specifications

Interpretable Reinforcement Learning with Multilevel Subgoal Discovery

DECORE: Deep Compression with Reinforcement Learning

Provable Reinforcement Learning with a Short-Term Memory

Learning Synthetic Environments and Reward Networks for Reinforcement Learning

Reinforcement Learning in Reward-Mixing MDPs

Reconciling Rewards with Predictive State Representations

Improving Model-Based Reinforcement Learning with Internal State Representations through Self-Supervision