AI Agent - arXivDaily 专题

1510.02879 2020-09-23 cs.AI cs.LG 62%

Attend, Adapt and Transfer: Attentive Deep Architecture for Adaptive Transfer from multiple sources in the same domain

Janarthanan Rajendran, Aravind Srinivas, Mitesh M. Khapra, P Prasanna, Balaraman Ravindran

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

Comments Published as a conference paper at ICLR 2017

2009.07518 2020-09-17 cs.LG cs.AI stat.ML 62%

Partial Bandit and Semi-Bandit: Making the Most Out of Scarce Users' Feedback

Alexandre Letard, Tassadit Amghar, Olivier Camp, Nicolas Gutowski

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

2006.15061 2020-09-14 cs.LG cs.AI stat.ML 62%

Intrinsic Reward Driven Imitation Learning via Generative Model

Xingrui Yu, Yueming Lyu, Ivor W. Tsang

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

2005.09980 2020-09-10 cs.AI cs.CL econ.GN q-fin.EC 62%

Artificial Intelligence versus Maya Angelou: Experimental evidence that people cannot differentiate AI-generated from human-written poetry

Nils Köbis, Luca Mossink

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

Comments Computers in Human Behavior 2020

2003.04518 2020-09-02 cs.AI cs.LG 62%

Exploring Unknown States with Action Balance

Yan Song, Yingfeng Chen, Yujing Hu, Changjie Fan

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

1909.10838 2020-08-27 cs.AI cs.CL cs.RO 62%

Talk2Car: Taking Control of Your Self-Driving Car

Thierry Deruyttere, Simon Vandenhende, Dusan Grujicic, Luc Van Gool, Marie-Francine Moens

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

Comments 14 pages, accepted at emnlp-ijcnlp 2019 - Added Talk2Nav Reference

1811.11298 2020-08-19 cs.LG cs.AI stat.ML 62%

Exploring Restart Distributions

Arash Tavakoli, Vitaly Levdik, Riashat Islam, Christopher M. Smith, Petar Kormushev

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

Comments RLDM 2019

2008.05660 2020-08-14 cs.LG cs.AI stat.ML 62%

Imitating Unknown Policies via Exploration

Nathan Gavenski, Juarez Monteiro, Roger Granada, Felipe Meneguzzi, Rodrigo C. Barros

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

Comments This paper has been accepted in the British Machine Vision Virtual Conference (BMVC) 2020

2004.11054 2020-08-14 cs.CL cs.LG cs.NE 62%

Learning Dialog Policies from Weak Demonstrations

Gabriel Gordon-Hall, Philip John Gorinski, Shay B. Cohen

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

Comments 9 pages + 2 pages references + 1 page appendices, 6 figures, 2 tables, 1 algorithm, accepted as long paper at ACL2020

1903.03698 2020-08-05 cs.LG cs.AI cs.RO stat.ML 62%

Skew-Fit: State-Covering Self-Supervised Reinforcement Learning

Vitchyr H. Pong, Murtaza Dalal, Steven Lin, Ashvin Nair, Shikhar Bahl, Sergey Levine

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

Comments ICML 2020. 8 pages, 8 figures; 9 pages appendix (6 additional figures)

2004.00567 2020-07-21 cs.LG cs.AI stat.ML 62%

Obstacle Tower Without Human Demonstrations: How Far a Deep Feed-Forward Network Goes with Reinforcement Learning

Marco Pleines, Jenia Jitsev, Mike Preuss, Frank Zimmer

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

Comments 8 pages, 9 figures, 2 tables, under review

2006.15757 2020-06-30 cs.LG cs.AI 62%

Exploring Optimal Control With Observations at a Cost

Rui Aguiar, Nikka Mofid, Hyunji Alex Nam

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

Comments 8 pages, 10 figures

1908.01289 2020-06-30 cs.LG cs.AI stat.ML 62%

Dueling Posterior Sampling for Preference-Based Reinforcement Learning

Ellen R. Novoseller, Yibing Wei, Yanan Sui, Yisong Yue, Joel W. Burdick

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

Comments To appear in Conference on Uncertainty in Artificial Intelligence (UAI), 2020. 9 pages before references and appendix; 51 pages total; 7 figures; 4 tables. This replacement incorporates reviewer comments, and in comparison to version 1, extends the theoretical and empirical analyses and adds mathematical detail. Code: https://github.com/ernovoseller/DuelingPosteriorSampling

2006.15223 2020-06-30 cs.AI cs.LG 62%

Perception-Prediction-Reaction Agents for Deep Reinforcement Learning

Adam Stooke, Valentin Dalibard, Siddhant M. Jayakumar, Wojciech M. Czarnecki, Max Jaderberg

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

2006.12478 2020-06-23 cs.LG cs.AI stat.ML 62%

Ecological Reinforcement Learning

John D. Co-Reyes, Suvansh Sanjeev, Glen Berseth, Abhishek Gupta, Sergey Levine

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

Comments Preprint. Website at: https://sites.google.com/view/ecological-rl/home

2006.08714 2020-06-17 cs.LG cs.AI stat.ML 62%

Latent Bandits Revisited

Joey Hong, Branislav Kveton, Manzil Zaheer, Yinlam Chow, Amr Ahmed, Craig Boutilier

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

Comments 16 pages, 2 figures

2006.05832 2020-06-16 cs.NE cs.AI cs.LG 62%

Adaptive Reinforcement Learning through Evolving Self-Modifying Neural Networks

Samuel Schmidgall

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

Comments GECCO'2020 Poster: Submitted and accepted

Journal ref Proc. of GECCO 2020

2006.03713 2020-06-09 cs.LG cs.AI stat.ML 62%

State Action Separable Reinforcement Learning

Ziyao Zhang, Liang Ma, Kin K. Leung, Konstantinos Poularakis, Mudhakar Srivatsa

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

Comments 16 pages

2006.01921 2020-06-04 cs.HC cs.AI cs.LG 62%

Offline and Online Satisfaction Prediction in Open-Domain Conversational Systems

Jason Ingyu Choi, Ali Ahmadvand, Eugene Agichtein

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

Comments Published in CIKM '19, 10 pages

1902.08039 2020-05-27 cs.LG cs.AI stat.ML 62%

Curiosity-Driven Experience Prioritization via Density Estimation

Rui Zhao, Volker Tresp

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

Comments Accepted by NIPS Deep RL Workshop, 2018, link: https://sites.google.com/view/deep-rl-workshop-nips-2018 . arXiv admin note: substantial text overlap with arXiv:1810.01363 and text overlap with arXiv:1905.08786

1909.02982 2020-05-26 cs.LG cs.AI cs.HC cs.NE stat.ML 62%

DRLViz: Understanding Decisions and Memory in Deep Reinforcement Learning

Theo Jaunet, Romain Vuillemot, Christian Wolf

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

1810.01363 2020-05-26 cs.LG cs.AI stat.ML 62%

Energy-Based Hindsight Experience Prioritization

Rui Zhao, Volker Tresp

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

Comments Published in Conference on Robot Learning (CoRL 2018) as oral presentation (7%), Zurich, Switzerland

Journal ref PMLR 87:113-122, 2018

2005.07541 2020-05-18 cs.LG cs.AI cs.RO stat.ML 62%

Simple Sensor Intentions for Exploration

Tim Hertweck, Martin Riedmiller, Michael Bloesch, Jost Tobias Springenberg, Noah Siegel, Markus Wulfmeier, Roland Hafner, Nicolas Heess

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

2005.06105 2020-05-18 cs.LG cs.AI 62%

Proxy Experience Replay: Federated Distillation for Distributed Reinforcement Learning

Han Cha, Jihong Park, Hyesung Kim, Mehdi Bennis, Seong-Lyun Kim

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

Comments 8 pages, 5 figures, This paper is accepted to IEEE Intelligent Systems special issue of July/Aug 2020 - Federated Machine Learning

2005.07099 2020-05-15 cs.CR cs.AI cs.LG 62%

Stealthy and Efficient Adversarial Attacks against Deep Reinforcement Learning

Jianwen Sun, Tianwei Zhang, Xiaofei Xie, Lei Ma, Yan Zheng, Kangjie Chen, Yang Liu

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

2005.04912 2020-05-12 cs.AI cs.LG 62%

Maximizing Information Gain in Partially Observable Environments via Prediction Reward

Yash Satsangi, Sungsu Lim, Shimon Whiteson, Frans Oliehoek, Martha White

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

Journal ref AAMAS 2020

2005.03789 2020-05-11 cs.LG cs.AI stat.ML 62%

Reinforcement Learning with Feedback Graphs

Christoph Dann, Yishay Mansour, Mehryar Mohri, Ayush Sekhari, Karthik Sridharan

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

2005.03648 2020-05-08 cs.LG cs.AI stat.ML 62%

Plan2Vec: Unsupervised Representation Learning by Latent Plans

Ge Yang, Amy Zhang, Ari S. Morcos, Joelle Pineau, Pieter Abbeel, Roberto Calandra

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

Comments code available at https://geyang.github.io/plan2vec

Journal ref Proceedings of Machine Learning Research, the 2nd Annual Conference on Learning for Dynamics and Control (2020) Volume 120, 1-12

2004.14646 2020-05-01 cs.LG cs.AI 62%

Bootstrap Latent-Predictive Representations for Multitask Reinforcement Learning

Daniel Guo, Bernardo Avila Pires, Bilal Piot, Jean-bastien Grill, Florent Altché, Rémi Munos, Mohammad Gheshlaghi Azar

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

1911.03768 2020-04-30 cs.CL cs.AI 62%

The Dialogue Dodecathlon: Open-Domain Knowledge and Image Grounded Conversational Agents

Kurt Shuster, Da Ju, Stephen Roller, Emily Dinan, Y-Lan Boureau, Jason Weston

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

Comments ACL 2020

1. 记忆与上下文管理 4753 篇

Attend, Adapt and Transfer: Attentive Deep Architecture for Adaptive Transfer from multiple sources in the same domain

Partial Bandit and Semi-Bandit: Making the Most Out of Scarce Users' Feedback

Intrinsic Reward Driven Imitation Learning via Generative Model

Artificial Intelligence versus Maya Angelou: Experimental evidence that people cannot differentiate AI-generated from human-written poetry

Exploring Unknown States with Action Balance

Talk2Car: Taking Control of Your Self-Driving Car

Exploring Restart Distributions

Imitating Unknown Policies via Exploration

Learning Dialog Policies from Weak Demonstrations

Skew-Fit: State-Covering Self-Supervised Reinforcement Learning

Obstacle Tower Without Human Demonstrations: How Far a Deep Feed-Forward Network Goes with Reinforcement Learning

Exploring Optimal Control With Observations at a Cost

Dueling Posterior Sampling for Preference-Based Reinforcement Learning

Perception-Prediction-Reaction Agents for Deep Reinforcement Learning

Ecological Reinforcement Learning

Latent Bandits Revisited

Adaptive Reinforcement Learning through Evolving Self-Modifying Neural Networks

State Action Separable Reinforcement Learning

Offline and Online Satisfaction Prediction in Open-Domain Conversational Systems

Curiosity-Driven Experience Prioritization via Density Estimation

DRLViz: Understanding Decisions and Memory in Deep Reinforcement Learning

Energy-Based Hindsight Experience Prioritization

Simple Sensor Intentions for Exploration

Proxy Experience Replay: Federated Distillation for Distributed Reinforcement Learning

Stealthy and Efficient Adversarial Attacks against Deep Reinforcement Learning

Maximizing Information Gain in Partially Observable Environments via Prediction Reward

Reinforcement Learning with Feedback Graphs

Plan2Vec: Unsupervised Representation Learning by Latent Plans

Bootstrap Latent-Predictive Representations for Multitask Reinforcement Learning

The Dialogue Dodecathlon: Open-Domain Knowledge and Image Grounded Conversational Agents