AI Agent - arXivDaily 专题

2209.05206 2022-09-13 cs.LG cs.AI 62%

A Differentiable Loss Function for Learning Heuristics in A*

Leah Chrestien, Tomas Pevny, Antonin Komenda, Stefan Edelkamp

专题命中工具调用：planning(abstract)；分类 cs.AI、cs.LG

Comments 10 pages

2208.12878 2022-08-30 cs.LG cs.AI cs.CR 62%

DETERRENT: Detecting Trojans using Reinforcement Learning

Vasudev Gohil, Satwik Patnaik, Hao Guo, Dileep Kalathil, Jeyavijayan, Rajendran

专题命中工具调用：agent(abstract)；分类 cs.AI、cs.LG

Comments Published in 2022 Design Automation Conference (DAC)

2208.11535 2022-08-25 cs.LG cs.AI 62%

A model-based approach to meta-Reinforcement Learning: Transformers and tree search

Brieuc Pinon, Jean-Charles Delvenne, Raphaël Jungers

专题命中工具调用：planning(abstract)；分类 cs.AI、cs.LG

2208.08552 2022-08-19 cs.AI cs.HC cs.LG cs.LO 62%

A Framework for Understanding and Visualizing Strategies of RL Agents

Pedro Sequeira, Daniel Elenius, Jesse Hostetler, Melinda Gervasio

专题命中工具调用：agent(abstract)；分类 cs.AI、cs.LG

2208.06894 2022-08-16 cs.CV cs.AI cs.LG 62%

The SVD of Convolutional Weights: A CNN Interpretability Framework

Brenda Praggastis, Davis Brown, Carlos Ortiz Marrero, Emilie Purvine, Madelyn Shapiro, Bei Wang

专题命中工具调用：tool use(abstract)；分类 cs.AI、cs.LG

2206.13396 2022-08-11 cs.CV cs.AI cs.LG cs.RO 62%

A Simple Approach for Visual Rearrangement: 3D Mapping and Semantic Search

Brandon Trabucco, Gunnar Sigurdsson, Robinson Piramuthu, Gaurav S. Sukhatme, Ruslan Salakhutdinov

专题命中工具调用：agent(abstract)；分类 cs.AI、cs.LG

Comments Winner of the Rearrangement Challenge at CVPR 2022

2012.11293 2022-08-08 cs.LG cs.AI physics.chem-ph 62%

Curiosity in exploring chemical space: Intrinsic rewards for deep molecular reinforcement learning

Luca A. Thiede, Mario Krenn, AkshatKumar Nigam, Alan Aspuru-Guzik

专题命中工具调用：agent(abstract)；分类 cs.AI、cs.LG

Comments 9 pages, 2 figures; comments welcome

Journal ref Machine Learning: Science and Technology 3, 035008 (2022)

2207.14722 2022-08-01 cs.LG cs.AI 62%

Automatic Reward Design via Learning Motivation-Consistent Intrinsic Rewards

Yixiang Wang, Yujing Hu, Feng Wu, Yingfeng Chen

专题命中工具调用：agent(abstract)；分类 cs.AI、cs.LG

2207.14140 2022-07-29 cs.LG cs.AI 62%

Playing a 2D Game Indefinitely using NEAT and Reinforcement Learning

Jerin Paul Selvan, Pravin S. Game

专题命中工具调用：agent(abstract)；分类 cs.AI、cs.LG

Comments 5 pages, 7 figures, 3 tables

2207.10342 2022-07-29 cs.CL cs.AI 62%

Language Model Cascades

David Dohan, Winnie Xu, Aitor Lewkowycz, Jacob Austin, David Bieber, Raphael Gontijo Lopes, Yuhuai Wu, Henryk Michalewski, Rif A. Saurous, Jascha Sohl-dickstein, Kevin Murphy, Charles Sutton

专题命中工具调用：tool use(abstract)；分类 cs.AI、cs.CL

Comments Presented as spotlight at the Beyond Bases workshop at ICML 2022 (https://beyond-bayes.github.io)

2207.09405 2022-07-20 cs.LG cs.AI 62%

Bayesian Generational Population-Based Training

Xingchen Wan, Cong Lu, Jack Parker-Holder, Philip J. Ball, Vu Nguyen, Binxin Ru, Michael A. Osborne

专题命中工具调用：agent(abstract)；分类 cs.AI、cs.LG

Comments AutoML Conference 2022. 10 pages, 4 figure, 3 tables (28 pages, 10 figures, 7 tables including references and appendices)

2206.12765 2022-06-28 cs.AI cs.LG 62%

Generalized Beliefs for Cooperative AI

Darius Muglich, Luisa Zintgraf, Christian Schroeder de Witt, Shimon Whiteson, Jakob Foerster

专题命中工具调用：agent(abstract)；分类 cs.AI、cs.LG

2206.06965 2022-06-15 cs.LG cs.AI cs.RO math.OC 62%

Deep Reinforcement Learning for Exact Combinatorial Optimization: Learning to Branch

Tianyu Zhang, Amin Banitalebi-Dehkordi, Yong Zhang

专题命中工具调用：agent(abstract)；分类 cs.AI、cs.LG

Comments ICPR 2022 Oral

2205.15281 2022-05-31 cs.CL cs.AI 62%

Learning Open Domain Multi-hop Search Using Reinforcement Learning

Enrique Noriega-Atala, Mihai Surdeanu, Clayton T. Morrison

专题命中工具调用：agent(abstract)；分类 cs.AI、cs.CL

Comments Accepted for publication at the Structured and Unstructured Knowledge Integration (SUKI) workshop, held at NAACL-HLT 2022

1708.02190 2022-05-06 cs.AI cs.LG 62%

Intrinsically Motivated Goal Exploration Processes with Automatic Curriculum Learning

Sébastien Forestier, Rémy Portelas, Yoan Mollard, Pierre-Yves Oudeyer

专题命中工具调用：tool use(abstract)；分类 cs.AI、cs.LG

Comments Accepted at JMLR 2022

2204.13812 2022-05-02 cs.HC cs.AI cs.GR cs.LG 62%

Visualization and Optimization Techniques for High Dimensional Parameter Spaces

Anjul Tyagi

专题命中工具调用：agent(abstract)；分类 cs.AI、cs.LG

Comments Report. arXiv admin note: substantial text overlap with arXiv:1907.12627

2202.03666 2022-04-18 cs.LG cs.AI cs.NE 62%

Approximating Gradients for Differentiable Quality Diversity in Reinforcement Learning

Bryon Tjanaka, Matthew C. Fontaine, Julian Togelius, Stefanos Nikolaidis

专题命中工具调用：agent(abstract)；分类 cs.AI、cs.LG

Comments Published as a conference paper at the 2022 Genetic and Evolutionary Computation Conference (GECCO '22); Online article available at http://dqd-rl.github.io

2203.15030 2022-03-31 cs.AI cs.LG cs.MA cs.RO cs.SY eess.SY 62%

Solving Disjunctive Temporal Networks with Uncertainty under Restricted Time-Based Controllability using Tree Search and Graph Neural Networks

Kevin Osanlou, Jeremy Frank, Andrei Bursuc, Tristan Cazenave, Eric Jacopin, Christophe Guettier, J. Benton

专题命中工具调用：planning(abstract)；分类 cs.AI、cs.LG

Comments Thirty-Sixth AAAI Conference on Artificial Intelligence. This version includes the technical appendix. arXiv admin note: substantial text overlap with arXiv:2108.01068

Journal ref Thirty-Sixth AAAI Conference on Artificial Intelligence, 2022

2103.17228 2022-03-07 cs.LG cs.AI 62%

OLIVAW: Mastering Othello without Human Knowledge, nor a Fortune

Antonio Norelli, Alessandro Panconesi

专题命中工具调用：agent(abstract)；分类 cs.AI、cs.LG

Comments Accepted for publication in IEEE Transactions on Games. Presented at AAAI-21 Reinforcement Learning in Games Workshop, 8 pages

2203.01027 2022-03-03 cs.LG cs.AI cs.NE 62%

Learning in Sparse Rewards settings through Quality-Diversity algorithms

Giuseppe Paolo

专题命中工具调用：agent(abstract)；分类 cs.AI、cs.LG

Comments PhD Thesis

2202.09196 2022-02-21 cs.LG cs.AI 62%

An Integrated Optimization and Machine Learning Models to Predict the Admission Status of Emergency Patients

Abdulaziz Ahmed, Omar Ashour, Haneen Ali, Mohammad Firouz

专题命中工具调用：planning(abstract)；分类 cs.AI、cs.LG

2202.07071 2022-02-16 cs.AI cs.LG 62%

A Unified Perspective on Value Backup and Exploration in Monte-Carlo Tree Search

Tuan Dam, Carlo D'Eramo, Jan Peters, Joni Pajarinen

专题命中工具调用：planning(abstract)；分类 cs.AI、cs.LG

Comments arXiv admin note: text overlap with arXiv:2007.00391

2202.05843 2022-02-15 cs.LG cs.AI cs.SY eess.SY 62%

Fast Model-based Policy Search for Universal Policy Networks

Buddhika Laknath Semage, Thommen George Karimpanal, Santu Rana, Svetha Venkatesh

专题命中工具调用：agent(abstract)；分类 cs.AI、cs.LG

2202.00658 2022-02-02 cs.LG cs.AI 62%

Scalable Fragment-Based 3D Molecular Design with Reinforcement Learning

Daniel Flam-Shepherd, Alexander Zhigalin, Alán Aspuru-Guzik

专题命中工具调用：agent(abstract)；分类 cs.AI、cs.LG

2108.13643 2022-02-02 cs.LG cs.AI cs.PL 62%

Learning to Synthesize Programs as Interpretable and Generalizable Policies

Dweep Trivedi, Jesse Zhang, Shao-Hua Sun, Joseph J. Lim

专题命中工具调用：agent(abstract)；分类 cs.AI、cs.LG

Comments NeurIPS 2021. 53 pages, 16 figures, 12 tables. Website at https://clvrai.github.io/leaps/

2201.12385 2022-02-01 cs.CV cs.AI cs.LG eess.IV eess.SP 62%

A deep Q-learning method for optimizing visual search strategies in backgrounds of dynamic noise

Weimin Zhou, Miguel P. Eckstein

专题命中工具调用：planning(abstract)；分类 cs.AI、cs.LG

Comments SPIE Medical Imaging 2022

2201.08742 2022-01-24 cs.IR cs.AI cs.CL 62%

Towards Building Economic Models of Conversational Search

Leif Azzopardi, Mohammad Aliannejadi, Evangelos Kanoulas

专题命中工具调用：agent(abstract)；分类 cs.AI、cs.CL

Comments To appear in ECIR 2022

2201.07096 2022-01-19 cs.SE cs.AI 62%

Lifelong Dynamic Optimization for Self-Adaptive Systems: Fact or Fiction?

Tao Chen

专题命中工具调用：planning(abstract)；分类 cs.AI、cs.SE

Comments The paper has been accepted as a full technical paper at the 29th IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER 2022)

2112.05779 2021-12-14 quant-ph cs.AI cs.ET cs.LG cs.NE 62%

Quantum Architecture Search via Continual Reinforcement Learning

Esther Ye, Samuel Yen-Chi Chen

专题命中工具调用：agent(abstract)；分类 cs.AI、cs.LG

2112.04467 2021-12-09 cs.LG cs.AI cs.RO 62%

CoMPS: Continual Meta Policy Search

Glen Berseth, Zhiwei Zhang, Grace Zhang, Chelsea Finn, Sergey Levine

专题命中工具调用：agent(abstract)；分类 cs.AI、cs.LG

Comments 23 pages, under review

1. 工具调用 5118 篇

A Differentiable Loss Function for Learning Heuristics in A*

DETERRENT: Detecting Trojans using Reinforcement Learning

A model-based approach to meta-Reinforcement Learning: Transformers and tree search

A Framework for Understanding and Visualizing Strategies of RL Agents

The SVD of Convolutional Weights: A CNN Interpretability Framework

A Simple Approach for Visual Rearrangement: 3D Mapping and Semantic Search

Curiosity in exploring chemical space: Intrinsic rewards for deep molecular reinforcement learning

Automatic Reward Design via Learning Motivation-Consistent Intrinsic Rewards

Playing a 2D Game Indefinitely using NEAT and Reinforcement Learning

Language Model Cascades

Bayesian Generational Population-Based Training

Generalized Beliefs for Cooperative AI

Deep Reinforcement Learning for Exact Combinatorial Optimization: Learning to Branch

Learning Open Domain Multi-hop Search Using Reinforcement Learning

Intrinsically Motivated Goal Exploration Processes with Automatic Curriculum Learning

Visualization and Optimization Techniques for High Dimensional Parameter Spaces

Approximating Gradients for Differentiable Quality Diversity in Reinforcement Learning

Solving Disjunctive Temporal Networks with Uncertainty under Restricted Time-Based Controllability using Tree Search and Graph Neural Networks

OLIVAW: Mastering Othello without Human Knowledge, nor a Fortune

Learning in Sparse Rewards settings through Quality-Diversity algorithms

An Integrated Optimization and Machine Learning Models to Predict the Admission Status of Emergency Patients

A Unified Perspective on Value Backup and Exploration in Monte-Carlo Tree Search

Fast Model-based Policy Search for Universal Policy Networks

Scalable Fragment-Based 3D Molecular Design with Reinforcement Learning

Learning to Synthesize Programs as Interpretable and Generalizable Policies

A deep Q-learning method for optimizing visual search strategies in backgrounds of dynamic noise

Towards Building Economic Models of Conversational Search

Lifelong Dynamic Optimization for Self-Adaptive Systems: Fact or Fiction?

Quantum Architecture Search via Continual Reinforcement Learning

CoMPS: Continual Meta Policy Search