AI Agent - arXivDaily 专题

2201.04735 2022-03-24 cs.LG cs.DS math.OC stat.ML 83%

Planning in Observable POMDPs in Quasipolynomial Time

Noah Golowich, Ankur Moitra, Dhruv Rohatgi

专题命中规划决策：planning(title,abstract)；agent(abstract)；分类 cs.LG

Comments 52 pages

2203.03485 2022-03-08 cs.AI 83%

Self-directed Learning of Action Models using Exploratory Planning

Dustin Dannenhauer, Matthew Molineaux, Michael W. Floyd, Noah Reifsnyder, David W. Aha

专题命中规划决策：planning(title,abstract)；agent(abstract)；分类 cs.AI

Comments Presented at The Ninth Advances in Cognitive Systems (ACS) Conference 2021 (arXiv:2201.06134)

2106.08417 2022-03-08 cs.CV cs.LG cs.RO 83%

Scene Transformer: A unified architecture for predicting multiple agent trajectories

Jiquan Ngiam, Benjamin Caine, Vijay Vasudevan, Zhengdong Zhang, Hao-Tien Lewis Chiang, Jeffrey Ling, Rebecca Roelofs, Alex Bewley, Chenxi Liu, Ashish Venugopal, David Weiss, Ben Sapp, Zhifeng Chen, Jonathon Shlens

专题命中规划决策：agent(title,abstract)；planning(abstract)；分类 cs.LG

Comments ICLR 2022

2106.06768 2022-02-17 cs.AI 83%

Planning Spatial Networks with Monte Carlo Tree Search

Victor-Alexandru Darvariu, Stephen Hailes, Mirco Musolesi

专题命中规划决策：planning(title,abstract)；agent(abstract)；分类 cs.AI

2110.09771 2022-02-15 cs.LG cs.GT stat.ML 83%

On Reward-Free RL with Kernel and Neural Function Approximations: Single-Agent MDP and Markov Game

Shuang Qiu, Jieping Ye, Zhaoran Wang, Zhuoran Yang

专题命中规划决策：agent(title,abstract)；planning(abstract)；分类 cs.LG

Comments ICML 2021

2202.04611 2022-02-10 cs.AI 83%

Task Modifiers for HTN Planning and Acting

Weihang Yuan, Hector Munoz-Avila, Venkatsampath Raja Gogineni, Sravya Kondrakunta, Michael Cox, Lifang He

专题命中规划决策：planning(title,abstract)；agent(abstract)；分类 cs.AI

Comments Presented at The Ninth Advances in Cognitive Systems (ACS) Conference 2021 (arXiv:2201.06134)

2108.05533 2022-02-08 cs.LG math.OC stat.ML 83%

Efficient Local Planning with Linear Function Approximation

Dong Yin, Botao Hao, Yasin Abbasi-Yadkori, Nevena Lazić, Csaba Szepesvári

专题命中规划决策：planning(title,abstract)；agent(abstract)；分类 cs.LG

Comments Algorithmic Learning Theory 2022

2010.06917 2022-02-07 cs.RO cs.LG 83%

UAV Path Planning using Global and Local Map Information with Deep Reinforcement Learning

Mirco Theile, Harald Bayerlein, Richard Nai, David Gesbert, Marco Caccamo

专题命中规划决策：planning(title,abstract)；agent(abstract)；分类 cs.LG

Comments ICAR 2021, code available at https://github.com/theilem/uavSim

2201.10335 2022-01-26 cs.LG 83%

Tracking and Planning with Spatial World Models

Baris Kayalibay, Atanas Mirchev, Patrick van der Smagt, Justin Bayer

专题命中规划决策：planning(title,abstract)；agent(abstract)；分类 cs.LG

2201.00411 2022-01-04 cs.CV cs.AI 83%

The Introspective Agent: Interdependence of Strategy, Physiology, and Sensing for Embodied Agents

Sarah Pratt, Luca Weihs, Ali Farhadi

专题命中规划决策：agent(title,abstract)；planning(abstract)；分类 cs.AI

2112.00903 2021-12-03 cs.AI cs.RO 83%

Modeling human intention inference in continuous 3D domains by inverse planning and body kinematics

Yingdong Qian, Marta Kryven, Tao Gao, Hanbyul Joo, Josh Tenenbaum

专题命中规划决策：planning(title,abstract)；agent(abstract)；分类 cs.AI

2102.03064 2021-12-03 cs.AI 83%

"I Don't Think So": Summarizing Policy Disagreements for Agent Comparison

Yotam Amitai, Ofra Amir

专题命中规划决策：agent(title,abstract)；autonomous agent(abstract)；分类 cs.AI

2111.04972 2021-11-10 cs.LG 83%

Risk Sensitive Model-Based Reinforcement Learning using Uncertainty Guided Planning

Stefan Radic Webster, Peter Flach

专题命中规划决策：planning(title,abstract)；agent(abstract)；分类 cs.LG

Comments Safe RL Workshop NeurIPS 2021

2110.00898 2021-10-05 cs.AI 83%

A Novel Automated Curriculum Strategy to Solve Hard Sokoban Planning Instances

Dieqiao Feng, Carla P. Gomes, Bart Selman

专题命中规划决策：planning(title,abstract)；agent(abstract)；分类 cs.AI

2106.08826 2021-10-01 math.OC cs.AI 83%

A discrete optimisation approach for target path planning whilst evading sensors

J. E. Beasley

专题命中规划决策：planning(title,abstract)；agent(abstract)；分类 cs.AI

2109.14325 2021-09-30 cs.RO cs.AI 83%

Improving Safety in Deep Reinforcement Learning using Unsupervised Action Planning

Hao-Lun Hsu, Qiuhua Huang, Sehoon Ha

专题命中规划决策：planning(title,abstract)；agent(abstract)；分类 cs.AI

2109.13978 2021-09-30 cs.AI 83%

Identifying Reasoning Flaws in Planning-Based RL Using Tree Explanations

Kin-Ho Lam, Zhengxian Lin, Jed Irvine, Jonathan Dodge, Zeyad T Shureih, Roli Khanna, Minsuk Kahng, Alan Fern

专题命中规划决策：planning(title,abstract)；agent(abstract)；分类 cs.AI

2109.00449 2021-09-08 cs.AI 83%

Planning from video game descriptions

Ignacio Vellido, Carlos Núñez-Molina, Vladislav Nikolov, Juan Fdez-Olivares

专题命中规划决策：planning(title,abstract)；agent(abstract)；分类 cs.AI

Comments To be submitted to the Knowledge Engineering Review (KER) journal

2105.00525 2021-09-07 cs.AI 83%

Planning for Proactive Assistance in Environments with Partial Observability

Anagha Kulkarni, Siddharth Srivastava, Subbarao Kambhampati

专题命中规划决策：planning(title)；agent(abstract)；AI agent(abstract)；分类 cs.AI

2108.11945 2021-08-27 cs.RO cs.CL cs.CV 83%

SASRA: Semantically-aware Spatio-temporal Reasoning Agent for Vision-and-Language Navigation in Continuous Environments

Muhammad Zubair Irshad, Niluthpol Chowdhury Mithun, Zachary Seymour, Han-Pang Chiu, Supun Samarasekera, Rakesh Kumar

专题命中规划决策：agent(title,abstract)；autonomous agent(abstract)；分类 cs.CL

Comments 10 pages, 4 figures

2107.04303 2021-08-11 cs.AI 83%

Integrating Planning, Execution and Monitoring in the presence of Open World Novelties: Case Study of an Open World Monopoly Solver

Sriram Gopalakrishnan, Utkarsh Soni, Tung Thai, Panagiotis Lymperopoulos, Matthias Scheutz, Subbarao Kambhampati

专题命中规划决策：planning(title)；agent(abstract)；multi-agent(abstract)；分类 cs.AI

2005.09611 2021-07-29 cs.RO cs.AI cs.IT math.IT 83%

Information-Theoretic Abstractions for Planning in Agents with Computational Constraints

Daniel T. Larsson, Dipankar Maity, Panagiotis Tsiotras

专题命中规划决策：planning(title,abstract)；agent(abstract)；分类 cs.AI

Journal ref 2021 IEEE Robotics and Automation Letters (RA-L)

2107.12544 2021-07-28 cs.AI 83%

Human-Level Reinforcement Learning through Theory-Based Modeling, Exploration, and Planning

Pedro A. Tsividis, Joao Loula, Jake Burga, Nathan Foss, Andres Campero, Thomas Pouncy, Samuel J. Gershman, Joshua B. Tenenbaum

专题命中规划决策：planning(title,abstract)；agent(abstract)；分类 cs.AI

2011.06450 2021-07-23 cs.AI cs.CV 83%

A deep Q-Learning based Path Planning and Navigation System for Firefighting Environments

Manish Bhattarai, Manel Martinez-Ramon

专题命中规划决策：planning(title,abstract)；agent(abstract)；分类 cs.AI

Comments Accepted to ICAART2021

2105.04088 2021-05-11 cs.AI 83%

PEARL: Parallelized Expert-Assisted Reinforcement Learning for Scene Rearrangement Planning

Hanqing Wang, Zan Wang, Wei Liang, Lap-Fai Yu

专题命中规划决策：planning(title,abstract)；agent(abstract)；分类 cs.AI

Comments 7 pages, 4 figures

2104.07276 2021-04-16 cs.AI 83%

Adaptive Belief Discretization for POMDP Planning

Divya Grover, Christos Dimitrakakis

专题命中规划决策：planning(title,abstract)；agent(abstract)；分类 cs.AI

2103.10642 2021-04-12 cs.AI cs.RO 83%

Knowledge-Based Hierarchical POMDPs for Task Planning

Sergio A. Serrano, Elizabeth Santiago, Jose Martinez-Carranza, Eduardo Morales, L. Enrique Sucar

专题命中规划决策：planning(title,abstract)；agent(abstract)；分类 cs.AI

Journal ref Journal of Intelligent & Robotic Systems 101 (2021) 1-30

2011.08345 2021-04-07 cs.LG cs.RO 83%

Distilling a Hierarchical Policy for Planning and Control via Representation and Reinforcement Learning

Jung-Su Ha, Young-Jin Park, Hyeok-Joo Chae, Soon-Seo Park, Han-Lim Choi

专题命中规划决策：planning(title,abstract)；agent(abstract)；分类 cs.LG

Comments ICRA 2021, the first two authors contributed equally

2103.14489 2021-03-29 cs.AI cs.FL cs.SY eess.SY 83%

Probabilistic Planning with Preferences over Temporal Goals

Jie Fu

专题命中规划决策：planning(title,abstract)；agent(abstract)；分类 cs.AI

Comments 6 pages, 8 figures, Accepted by American Control Conference (ACC) 2021

2103.01171 2021-03-26 cs.AI 83%

Expected Value of Communication for Planning in Ad Hoc Teamwork

William Macke, Reuth Mirsky, Peter Stone

专题命中规划决策：planning(title,abstract)；autonomous agent(abstract)；分类 cs.AI

Comments 10 pages, 6 figure, Published at AAAI 2021

1. 规划决策 35471 篇

Planning in Observable POMDPs in Quasipolynomial Time

Self-directed Learning of Action Models using Exploratory Planning

Scene Transformer: A unified architecture for predicting multiple agent trajectories

Planning Spatial Networks with Monte Carlo Tree Search

On Reward-Free RL with Kernel and Neural Function Approximations: Single-Agent MDP and Markov Game

Task Modifiers for HTN Planning and Acting

Efficient Local Planning with Linear Function Approximation

UAV Path Planning using Global and Local Map Information with Deep Reinforcement Learning

Tracking and Planning with Spatial World Models

The Introspective Agent: Interdependence of Strategy, Physiology, and Sensing for Embodied Agents

Modeling human intention inference in continuous 3D domains by inverse planning and body kinematics

"I Don't Think So": Summarizing Policy Disagreements for Agent Comparison

Risk Sensitive Model-Based Reinforcement Learning using Uncertainty Guided Planning

A Novel Automated Curriculum Strategy to Solve Hard Sokoban Planning Instances

A discrete optimisation approach for target path planning whilst evading sensors

Improving Safety in Deep Reinforcement Learning using Unsupervised Action Planning

Identifying Reasoning Flaws in Planning-Based RL Using Tree Explanations

Planning from video game descriptions

Planning for Proactive Assistance in Environments with Partial Observability

SASRA: Semantically-aware Spatio-temporal Reasoning Agent for Vision-and-Language Navigation in Continuous Environments

Integrating Planning, Execution and Monitoring in the presence of Open World Novelties: Case Study of an Open World Monopoly Solver

Information-Theoretic Abstractions for Planning in Agents with Computational Constraints

Human-Level Reinforcement Learning through Theory-Based Modeling, Exploration, and Planning

A deep Q-Learning based Path Planning and Navigation System for Firefighting Environments

PEARL: Parallelized Expert-Assisted Reinforcement Learning for Scene Rearrangement Planning

Adaptive Belief Discretization for POMDP Planning

Knowledge-Based Hierarchical POMDPs for Task Planning

Distilling a Hierarchical Policy for Planning and Control via Representation and Reinforcement Learning

Probabilistic Planning with Preferences over Temporal Goals

Expected Value of Communication for Planning in Ad Hoc Teamwork