AI Agent - arXivDaily 专题

2206.01078 2022-11-11 cs.LG cs.AI 62%

Deep Transformer Q-Networks for Partially Observable Reinforcement Learning

Kevin Esslinger, Robert Platt, Christopher Amato

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

2210.04251 2022-11-09 cs.LG cs.AI 62%

State Advantage Weighting for Offline RL

Jiafei Lyu, Aicheng Gong, Le Wan, Zongqing Lu, Xiu Li

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

Comments 3rd Offline RL workshop at NeurIPS 2022. arXiv admin note: text overlap with arXiv:2206.07989

2211.03281 2022-11-08 cs.LG cs.AI 62%

Reward-Predictive Clustering

Lucas Lehnert, Michael J. Frank, Michael L. Littman

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

2211.02100 2022-11-07 cs.LG cs.AI 62%

Contrastive Value Learning: Implicit Models for Simple Offline RL

Bogdan Mazoure, Benjamin Eysenbach, Ofir Nachum, Jonathan Tompson

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

Comments Deep Reinforcement Learning Workshop, NeurIPS 2022

2210.10638 2022-11-07 cs.IR cs.AI cs.LG 62%

Digital Human Interactive Recommendation Decision-Making Based on Reinforcement Learning

Xiong Junwu, Xiaoyun Feng, YunZhou Shi, James Zhang, Zhongzhou Zhao, Wei Zhou

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

Comments 9 pages, 1 figure, 1 table, the paper has been accepted and this is the final camera-ready for NeurIPS 2022 Workshop on Human in the Loop Learning, https://neurips-hill.github.io/

2210.15670 2022-10-31 cs.LG cs.AI 62%

Knowledge-Guided Exploration in Deep Reinforcement Learning

Sahisnu Mazumder, Bing Liu, Shuai Wang, Yingxuan Zhu, Xiaotian Yin, Lifeng Liu, Jian Li

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

Comments This paper is an extended and revised version of the work: "Action permissibility in deep reinforcement learning and application to autonomous driving", KDD'18 Deep Learning Day (2018)

2210.13383 2022-10-25 cs.AI cs.LG 62%

Evaluating Long-Term Memory in 3D Mazes

Jurgis Pasukonis, Timothy Lillicrap, Danijar Hafner

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

Comments Project website: https://github.com/jurgisp/memory-maze

2210.09496 2022-10-25 cs.LG cs.AI 62%

CEIP: Combining Explicit and Implicit Priors for Reinforcement Learning with Demonstrations

Kai Yan, Alexander G. Schwing, Yu-Xiong Wang

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

Comments 27 pages; published as NeurIPS 2022 poster paper

2210.11348 2022-10-21 cs.LG cs.AI cs.RO 62%

Hypernetworks in Meta-Reinforcement Learning

Jacob Beck, Matthew Thomas Jackson, Risto Vuorio, Shimon Whiteson

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

Comments Published at CoRL 2022

2210.08384 2022-10-18 cs.CL cs.LG 62%

Revisiting the Roles of "Text" in Text Games

Yi Gu, Shunyu Yao, Chuang Gan, Joshua B. Tenenbaum, Mo Yu

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

2202.02363 2022-10-13 cs.LG cs.AI cs.NE math.OC 62%

Meta-Reinforcement Learning with Self-Modifying Networks

Mathieu Chalvidal, Thomas Serre, Rufin VanRullen

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

Comments Published at Neurips 2022

2210.04157 2022-10-11 cs.LG cs.AI math.OC stat.ML 62%

The Role of Coverage in Online Reinforcement Learning

Tengyang Xie, Dylan J. Foster, Yu Bai, Nan Jiang, Sham M. Kakade

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

2210.01231 2022-10-05 cs.LG cs.AI 62%

Interpretable Option Discovery using Deep Q-Learning and Variational Autoencoders

Per-Arne Andersen, Ole-Christoffer Granmo, Morten Goodwin

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

Comments 12 pages, 5 figures, Proceedings of the 3rd International Conference on Intelligent Technologies and Applications

Journal ref 2021 Springer Nature Switzerland AG

2210.00859 2022-10-04 cs.SE cs.LG 62%

Requirements Engineering for Machine Learning: A Review and Reflection

Zhongyi Pei, Lin Liu, Chen Wang, Jianmin Wang

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

2106.08746 2022-09-26 cs.LG cs.AI cs.CR 62%

Real-time Adversarial Perturbations against Deep Reinforcement Learning Policies: Attacks and Defenses

Buse G. A. Tekgul, Shelly Wang, Samuel Marchal, N. Asokan

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

Comments Will appear in the proceedings of ESORICS 2022; 13 pages, 6 figures, 6 tables

2209.07928 2022-09-23 cs.AI cs.CL cs.SY eess.SY 62%

The BLue Amazon Brain (BLAB): A Modular Architecture of Services about the Brazilian Maritime Territory

Paulo Pirozelli, Ais B. R. Castro, Ana Luiza C. de Oliveira, André S. Oliveira, Flávio N. Cação, Igor C. Silveira, João G. M. Campos, Laura C. Motheo, Leticia F. Figueiredo, Lucas F. A. O. Pellicer, Marcelo A. José, Marcos M. José, Pedro de M. Ligabue, Ricardo S. Grava, Rodrigo M. Tavares, Vinícius B. Matos, Yan V. Sym, Anna H. R. Costa, Anarosa A. F. Brandão, Denis D. Mauá, Fabio G. Cozman, Sarajane M. Peres

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

Journal ref AI: Modeling Oceans and Climate Change (IJCAI-ECAI), 2022

2209.09097 2022-09-20 cs.CV cs.AI cs.LG cs.RO 62%

Disentangling Shape and Pose for Object-Centric Deep Active Inference Models

Stefano Ferraro, Toon Van de Maele, Pietro Mazzaglia, Tim Verbelen, Bart Dhoedt

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

2205.13451 2022-09-20 cs.LG cs.AI stat.ML 62%

Follow-the-Perturbed-Leader for Adversarial Markov Decision Processes with Bandit Feedback

Yan Dai, Haipeng Luo, Liyu Chen

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

Comments Accepted to NeurIPS 2022

2209.05840 2022-09-14 cs.CL cs.AI 62%

Visual Recipe Flow: A Dataset for Learning Visual State Changes of Objects with Recipe Flows

Keisuke Shirai, Atsushi Hashimoto, Taichi Nishimura, Hirotaka Kameko, Shuhei Kurita, Yoshitaka Ushiku, Shinsuke Mori

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

Comments COLING 2022

2209.05302 2022-09-13 cs.LG cs.AI 62%

Unified State Representation Learning under Data Augmentation

Taylor Hearn, Sravan Jayanthi, Sehoon Ha

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

Comments 5 pages, 3 figures, 1 table, Georgia Tech CS 8803: Deep Reinforcement Learning for Intelligent Control

2209.01876 2022-09-07 cs.LG cs.AI cs.IR cs.NI cs.SI 62%

SlateFree: a Model-Free Decomposition for Reinforcement Learning with Slate Actions

Anastasios Giovanidis

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

Comments 12 pages, 9 sub-figures

2209.00459 2022-09-02 cs.AI cs.HC cs.LG 62%

Generative Personas That Behave and Experience Like Humans

Matthew Barthet, Ahmed Khalifa, Antonios Liapis, Georgios N. Yannakakis

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

Comments 10 pages, 6 figures

2208.04822 2022-08-31 cs.LG cs.AI 62%

Generalized Reinforcement Learning: Experience Particles, Action Operator, Reinforcement Field, Memory Association, and Decision Concepts

Po-Hsiang Chiu, Manfred Huber

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

Comments 37 pages, 15 figures

2208.05056 2022-08-17 cs.LG cs.AI 62%

Model-Free Generative Replay for Lifelong Reinforcement Learning: Application to Starcraft-2

Zachary Daniels, Aswin Raghavan, Jesse Hostetler, Abrar Rahman, Indranil Sur, Michael Piacentino, Ajay Divakaran

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

Comments Accepted to the First Conference on Lifelong Learning Agents (CoLLAs 2022)

2205.08926 2022-07-26 cs.AI cs.LG q-bio.NC 62%

Generating Explanations from Deep Reinforcement Learning Using Episodic Memory

Sam Blakeman, Denis Mareschal

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

2103.07011 2022-07-25 cs.CL cs.AI 62%

Towards Socially Intelligent Agents with Mental State Transition and Human Utility

Liang Qiu, Yizhou Zhao, Yuan Liang, Pan Lu, Weiyan Shi, Zhou Yu, Song-Chun Zhu

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

Comments Long paper accepted by SIGDIAL 2022

2207.07825 2022-07-19 cs.AI cs.LG 62%

ChronosPerseus: Randomized Point-based Value Iteration with Importance Sampling for POSMDPs

Richard Kohar, François Rivest, Alain Gosselin

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

Comments 33 pages, 9 figures

2207.02074 2022-07-06 cs.LG cs.AI cs.NI 62%

Resource Allocation in Multicore Elastic Optical Networks: A Deep Reinforcement Learning Approach

Juan Pinto-Ríos, Felipe Calderón, Ariel Leiva, Gabriel Hermosilla, Alejandra Beghelli, Danilo Bórquez-Paredes, Astrid Lozada, Nicolás Jara, Ricardo Olivares, Gabriel Saavedra

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

Comments 11 pages, 10 figures

2205.06111 2022-07-05 cs.AI cs.CL 62%

Asking for Knowledge: Training RL Agents to Query External Knowledge Using Language

Iou-Jen Liu, Xingdi Yuan, Marc-Alexandre Côté, Pierre-Yves Oudeyer, Alexander G. Schwing

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

Comments ICML 2022; Project page: https://ioujenliu.github.io/AFK/

2111.14737 2022-06-30 cs.GT cs.AI cs.LG cs.MA econ.TH 62%

Beyond Time-Average Convergence: Near-Optimal Uncoupled Online Learning via Clairvoyant Multiplicative Weights Update

Georgios Piliouras, Ryann Sim, Stratis Skoulakis

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

Comments Expanded on the uncoupled online nature of the dynamics

1. 记忆与上下文管理 4786 篇

Deep Transformer Q-Networks for Partially Observable Reinforcement Learning

State Advantage Weighting for Offline RL

Reward-Predictive Clustering

Contrastive Value Learning: Implicit Models for Simple Offline RL

Digital Human Interactive Recommendation Decision-Making Based on Reinforcement Learning

Knowledge-Guided Exploration in Deep Reinforcement Learning

Evaluating Long-Term Memory in 3D Mazes

CEIP: Combining Explicit and Implicit Priors for Reinforcement Learning with Demonstrations

Hypernetworks in Meta-Reinforcement Learning

Revisiting the Roles of "Text" in Text Games

Meta-Reinforcement Learning with Self-Modifying Networks

The Role of Coverage in Online Reinforcement Learning

Interpretable Option Discovery using Deep Q-Learning and Variational Autoencoders

Requirements Engineering for Machine Learning: A Review and Reflection

Real-time Adversarial Perturbations against Deep Reinforcement Learning Policies: Attacks and Defenses

The BLue Amazon Brain (BLAB): A Modular Architecture of Services about the Brazilian Maritime Territory

Disentangling Shape and Pose for Object-Centric Deep Active Inference Models

Follow-the-Perturbed-Leader for Adversarial Markov Decision Processes with Bandit Feedback

Visual Recipe Flow: A Dataset for Learning Visual State Changes of Objects with Recipe Flows

Unified State Representation Learning under Data Augmentation

SlateFree: a Model-Free Decomposition for Reinforcement Learning with Slate Actions

Generative Personas That Behave and Experience Like Humans

Generalized Reinforcement Learning: Experience Particles, Action Operator, Reinforcement Field, Memory Association, and Decision Concepts

Model-Free Generative Replay for Lifelong Reinforcement Learning: Application to Starcraft-2

Generating Explanations from Deep Reinforcement Learning Using Episodic Memory

Towards Socially Intelligent Agents with Mental State Transition and Human Utility

ChronosPerseus: Randomized Point-based Value Iteration with Importance Sampling for POSMDPs

Resource Allocation in Multicore Elastic Optical Networks: A Deep Reinforcement Learning Approach

Asking for Knowledge: Training RL Agents to Query External Knowledge Using Language

Beyond Time-Average Convergence: Near-Optimal Uncoupled Online Learning via Clairvoyant Multiplicative Weights Update