AI Agent - arXivDaily 专题

2109.02032 2021-09-07 cs.LG cs.AI cs.MA 84%

Soft Hierarchical Graph Recurrent Networks for Many-Agent Partially Observable Environments

Zhenhui Ye, Xiaohong Jiang, Guanghua Song, Bowei Yang

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

Comments 9 pages, 6 figures, 1 table. Under review

2108.01851 2021-08-05 cs.LG cs.AI cs.RO 84%

Risk Conditioned Neural Motion Planning

Xin Huang, Meng Feng, Ashkan Jasour, Guy Rosman, Brian Williams

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

Comments Accepted at IROS'21. Author version with 7 pages, 5 figures, 2 tables, and 1 algorithm

2106.04615 2021-06-11 cs.LG cs.AI stat.ML 84%

Vector Quantized Models for Planning

Sherjil Ozair, Yazhe Li, Ali Razavi, Ioannis Antonoglou, Aäron van den Oord, Oriol Vinyals

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

Comments ICML 2021

2010.11038 2021-06-10 cs.AI cs.LG 84%

Influence-Augmented Online Planning for Complex Environments

Jinke He, Miguel Suau, Frans A. Oliehoek

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

Comments NeurIPS2020 - results have been updated after fixing minor bugs in the code

2011.13897 2021-05-04 cs.LG cs.AI cs.RO stat.ML 84%

Latent Skill Planning for Exploration and Transfer

Kevin Xie, Homanga Bharadhwaj, Danijar Hafner, Animesh Garg, Florian Shkurti

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

Comments First two authors contributed equally. Published as a conference paper in ICLR 2021

2101.06832 2021-04-30 cs.CV cs.AI cs.LG cs.RO 84%

Deep Structured Reactive Planning

Jerry Liu, Wenyuan Zeng, Raquel Urtasun, Ersin Yumer

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

Comments ICRA 2021

2103.14025 2021-03-26 cs.CV cs.AI cs.LG cs.RO 84%

The ThreeDWorld Transport Challenge: A Visually Guided Task-and-Motion Planning Benchmark for Physically Realistic Embodied AI

Chuang Gan, Siyuan Zhou, Jeremy Schwartz, Seth Alter, Abhishek Bhandwaldar, Dan Gutfreund, Daniel L. K. Yamins, James J DiCarlo, Josh McDermott, Antonio Torralba, Joshua B. Tenenbaum

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

Comments Project page: http://tdw-transport.csail.mit.edu/

2007.02418 2021-03-09 cs.LG cs.AI stat.ML 84%

Selective Dyna-style Planning Under Limited Model Capacity

Zaheer Abbas, Samuel Sokota, Erin J. Talvitie, Martha White

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

Comments Accepted at ICML 2020

1909.12217 2021-01-27 eess.SP cs.AI cs.LG 84%

Visual Exploration and Energy-aware Path Planning via Reinforcement Learning

Amir Niaraki, Jeremy Roghair, Ali Jannesari

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

Comments 20 Pages, 14 figures

2007.13202 2020-11-10 cs.LG cs.AI cs.RO 84%

CAMPs: Learning Context-Specific Abstractions for Efficient Planning in Factored MDPs

Rohan Chitnis, Tom Silver, Beomjoon Kim, Leslie Pack Kaelbling, Tomas Lozano-Perez

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

Comments CoRL 2020

2011.01771 2020-11-06 cs.LG cs.AI cs.SY eess.SY 84%

Deep Reinforcement Learning Based Dynamic Route Planning for Minimizing Travel Time

Yuanzhe Geng, Erwu Liu, Rui Wang, Yiming Liu

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

2009.05524 2020-10-30 cs.AI cs.LG 84%

Physically Embedded Planning Problems: New Challenges for Reinforcement Learning

Mehdi Mirza, Andrew Jaegle, Jonathan J. Hunt, Arthur Guez, Saran Tunyasuvunakool, Alistair Muldal, Théophane Weber, Peter Karkus, Sébastien Racanière, Lars Buesing, Timothy Lillicrap, Nicolas Heess

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

Comments 17 pages + appendix. Updated text and references

2007.11121 2020-07-23 cs.LG cs.AI stat.ML 84%

PackIt: A Virtual Environment for Geometric Planning

Ankit Goyal, Jia Deng

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

Comments Accepted to ICML 2020

2007.05694 2020-07-14 cs.LG cs.AI cs.IT math.IT stat.ML 84%

Long-Term Planning with Deep Reinforcement Learning on Autonomous Drones

Ugurkan Ates

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

Comments Submitted to Association for the Advancement of Artificial Intelligence(AAAI) 2020 Fall Symposium Series

2007.01380 2020-07-06 cs.AI cs.LG math.OC stat.ML 84%

Deep reinforcement learning driven inspection and maintenance planning under incomplete information and constraints

C. P. Andriotis, K. G. Papakonstantinou

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

2005.05960 2020-07-02 cs.LG cs.AI cs.CV cs.NE cs.RO stat.ML 84%

Planning to Explore via Self-Supervised World Models

Ramanan Sekar, Oleh Rybkin, Kostas Daniilidis, Pieter Abbeel, Danijar Hafner, Deepak Pathak

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

Comments Accepted at ICML 2020. Videos and code at https://ramanans1.github.io/plan2explore/

2006.07430 2020-06-23 cs.AI cs.LG 84%

Continuous Control for Searching and Planning with a Learned Model

Xuxi Yang, Werner Duvaud, Peng Wei

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

1910.02330 2020-06-17 cs.LG cs.AI stat.ML 84%

Towards Deployment of Robust AI Agents for Human-Machine Partnerships

Ahana Ghosh, Sebastian Tschiatschek, Hamed Mahdavi, Adish Singla

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

2006.06620 2020-06-12 cs.RO cs.AI cs.LG 84%

From proprioception to long-horizon planning in novel environments: A hierarchical RL model

Nishad Gothoskar, Miguel Lázaro-Gredilla, Dileep George

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

2006.00900 2020-06-02 cs.LG cs.AI stat.ML 84%

PlanGAN: Model-based Planning With Sparse Rewards and Multiple Goals

Henry Charlesworth, Giovanni Montana

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

2003.08554 2020-03-20 cs.AI cs.LG 84%

Adjust Planning Strategies to Accommodate Reinforcement Learning Agents

Xuerun Chen

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

2003.04690 2020-03-11 cs.MA cs.AI cs.SE 84%

JS-son -- A Lean, Extensible JavaScript Agent Programming Library

Timotheus Kampik, Juan Carlos Nieves

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

Comments Accepted for the post-proceedings of EMAS 2019

1912.09996 2020-03-05 cs.LG cs.AI stat.ML 84%

Uncertainty-sensitive Learning and Planning with Ensembles

Piotr Miłoś, Łukasz Kuciński, Konrad Czechowski, Piotr Kozakowski, Maciek Klimek

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

1912.06721 2019-12-17 cs.CL cs.LG 84%

Long-Term Planning and Situational Awareness in OpenAI Five

Jonathan Raiman, Susan Zhang, Filip Wolski

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

1912.04201 2019-12-10 cs.LG cs.AI stat.ML 84%

Learning Latent State Spaces for Planning through Reward Prediction

Aaron Havens, Yi Ouyang, Prabhat Nagarajan, Yasuhiro Fujita

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

Comments Deep RL Workshop, Neurips 2019, Vancouver

1905.09683 2019-12-10 cs.LG cs.AI cs.RO 84%

From semantics to execution: Integrating action planning with reinforcement learning for robotic causal problem-solving

Manfred Eppe, Phuong D. H. Nguyen, Stefan Wermter

专题命中规划决策：planning(title,abstract)；tool use(abstract)；分类 cs.AI、cs.LG

1911.00229 2019-11-04 cs.CL cs.AI 84%

Engaging in Dialogue about an Agent's Norms and Behaviors

Daniel Kasenberg, Antonio Roque, Ravenna Thielstrom, Matthias Scheutz

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

Comments Accepted to the 1st Workshop on Interactive Natural Language Technology for Explainable Artificial Intelligence (NL4XAI)

1909.13870 2019-10-01 cs.LG cs.AI cs.RO 84%

Learning Compact Models for Planning with Exogenous Processes

Rohan Chitnis, Tomás Lozano-Pérez

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

Comments CoRL 2019 final version

1909.06034 2019-09-16 cs.LG cs.AI cs.RO cs.SY eess.SY stat.ML 84%

Deep Learned Path Planning via Randomized Reward-Linked-Goals and Potential Space Applications

Tamir Blum, William Jones, Kazuya Yoshida

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

Comments 8 pages, 3 tables, 5 figures

1902.01378 2019-07-03 cs.AI cs.LG 84%

Obstacle Tower: A Generalization Challenge in Vision, Control, and Planning

Arthur Juliani, Ahmed Khalifa, Vincent-Pierre Berges, Jonathan Harper, Ervin Teng, Hunter Henry, Adam Crespi, Julian Togelius, Danny Lange

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

Comments IJCAI 2019

1. 规划决策 35648 篇

Soft Hierarchical Graph Recurrent Networks for Many-Agent Partially Observable Environments

Risk Conditioned Neural Motion Planning

Vector Quantized Models for Planning

Influence-Augmented Online Planning for Complex Environments

Latent Skill Planning for Exploration and Transfer

Deep Structured Reactive Planning

The ThreeDWorld Transport Challenge: A Visually Guided Task-and-Motion Planning Benchmark for Physically Realistic Embodied AI

Selective Dyna-style Planning Under Limited Model Capacity

Visual Exploration and Energy-aware Path Planning via Reinforcement Learning

CAMPs: Learning Context-Specific Abstractions for Efficient Planning in Factored MDPs

Deep Reinforcement Learning Based Dynamic Route Planning for Minimizing Travel Time

Physically Embedded Planning Problems: New Challenges for Reinforcement Learning

PackIt: A Virtual Environment for Geometric Planning

Long-Term Planning with Deep Reinforcement Learning on Autonomous Drones

Deep reinforcement learning driven inspection and maintenance planning under incomplete information and constraints

Planning to Explore via Self-Supervised World Models

Continuous Control for Searching and Planning with a Learned Model

Towards Deployment of Robust AI Agents for Human-Machine Partnerships

From proprioception to long-horizon planning in novel environments: A hierarchical RL model

PlanGAN: Model-based Planning With Sparse Rewards and Multiple Goals

Adjust Planning Strategies to Accommodate Reinforcement Learning Agents

JS-son -- A Lean, Extensible JavaScript Agent Programming Library

Uncertainty-sensitive Learning and Planning with Ensembles

Long-Term Planning and Situational Awareness in OpenAI Five

Learning Latent State Spaces for Planning through Reward Prediction

From semantics to execution: Integrating action planning with reinforcement learning for robotic causal problem-solving

Engaging in Dialogue about an Agent's Norms and Behaviors

Learning Compact Models for Planning with Exogenous Processes

Deep Learned Path Planning via Randomized Reward-Linked-Goals and Potential Space Applications

Obstacle Tower: A Generalization Challenge in Vision, Control, and Planning