机器人 / 具身智能 - arXivDaily 专题

2403.18524 2024-03-28 cs.RO 57%

Bridging the Gap: Regularized Reinforcement Learning for Improved Classical Motion Planning with Safety Modules

Elias Goldsztejn, Ronen I. Brafman

专题命中模仿学习与强化学习：navigation(abstract)；分类 cs.RO

Comments 8 pages

2403.12210 2024-03-20 eess.SY cs.LG cs.SY 57%

Decomposing Control Lyapunov Functions for Efficient Reinforcement Learning

Antonio Lopez, David Fridovich-Keil

专题命中模仿学习与强化学习：robotics(abstract)；分类 cs.LG

2403.11219 2024-03-19 cs.AI 57%

Causality from Bottom to Top: A Survey

Abraham Itzhak Weinberg, Cristiano Premebida, Diego Resende Faria

专题命中模仿学习与强化学习：robotics(abstract)；分类 cs.AI

2303.10257 2024-03-12 math.OC cs.LG 57%

Recent Developments in Machine Learning Methods for Stochastic Control and Games

Ruimeng Hu, Mathieu Laurière

专题命中模仿学习与强化学习：robotics(abstract)；分类 cs.LG

2310.09714 2024-03-11 cs.RO 57%

Enhancing Task Performance of Learned Simplified Models via Reinforcement Learning

Hien Bui, Michael Posa

专题命中模仿学习与强化学习：robotic(abstract)；分类 cs.RO

Comments The work will be presented in ICRA2024

2403.01636 2024-03-07 stat.ML cs.LG 57%

Sample Efficient Myopic Exploration Through Multitask Reinforcement Learning with Diverse Tasks

Ziping Xu, Zifan Xu, Runxuan Jiang, Peter Stone, Ambuj Tewari

专题命中模仿学习与强化学习：robotic(abstract)；分类 cs.LG

2310.05808 2024-03-05 cs.RO 57%

An Open-Loop Baseline for Reinforcement Learning Locomotion Tasks

Antonin Raffin, Olivier Sigaud, Jens Kober, Alin Albu-Schäffer, João Silvério, Freek Stulp

专题命中模仿学习与强化学习：robotic(abstract)；分类 cs.RO

Comments video: https://b2drop.eudat.eu/s/ykDPMM7F9KFyLgi minimal code: https://gist.github.com/araffin/1fb77a8f290ac248b2e76e01164f21e0

2403.01059 2024-03-05 cs.LG 57%

Continuous Mean-Zero Disagreement-Regularized Imitation Learning (CMZ-DRIL)

Noah Ford, Ryan W. Gardner, Austin Juhl, Nathan Larson

专题命中模仿学习与强化学习：navigation(abstract)；分类 cs.LG

2309.08095 2024-03-05 cs.RO 57%

RELAX: Reinforcement Learning Enabled 2D-LiDAR Autonomous System for Parsimonious UAVs

Guanlin Wu, Zhuokai Zhao, Yutao He

专题命中模仿学习与强化学习：navigation(abstract)；分类 cs.RO

2308.13654 2024-03-05 cs.LG 57%

Pretty darn good control: when are approximate solutions better than approximate models

Felipe Montealegre-Mora, Marcus Lapeyrolerie, Melissa Chapman, Abigail G. Keller, Carl Boettiger

专题命中模仿学习与强化学习：robotic(abstract)；分类 cs.LG

Comments 24 pages, 14 figures. Accepted to the Bulletin of Mathematical Biology

2307.06175 2024-02-26 cs.LG cs.MA math.OC 57%

Learning Decentralized Partially Observable Mean Field Control for Artificial Collective Behavior

Kai Cui, Sascha Hauck, Christian Fabian, Heinz Koeppl

专题命中模仿学习与强化学习：robotic(abstract)；分类 cs.LG

Comments Accepted to ICLR 2024

2402.13419 2024-02-22 cs.AI 57%

Reward Bound for Behavioral Guarantee of Model-based Planning Agents

Zhiyu An, Xianzhong Ding, Wan Du

专题命中模仿学习与强化学习：robotics(abstract)；分类 cs.AI

Comments To be published in ICLR 24 tiny paper track

2402.07019 2024-02-13 cs.LG 57%

Informativeness of Reward Functions in Reinforcement Learning

Rati Devidze, Parameswaran Kamalaruban, Adish Singla

专题命中模仿学习与强化学习：navigation(abstract)；分类 cs.LG

Comments Longer version of the AAMAS'24 paper

2402.01913 2024-02-06 cs.RO 57%

TartanDrive 2.0: More Modalities and Better Infrastructure to Further Self-Supervised Learning Research in Off-Road Driving Tasks

Matthew Sivaprakasam, Parv Maheshwari, Mateo Guaman Castro, Samuel Triest, Micah Nye, Steve Willits, Andrew Saba, Wenshan Wang, Sebastian Scherer

专题命中模仿学习与强化学习：robotics(abstract)；分类 cs.RO

2206.11396 2024-01-30 cs.LG 57%

Multi-Horizon Representations with Hierarchical Forward Models for Reinforcement Learning

Trevor McInroe, Lukas Schäfer, Stefano V. Albrecht

专题命中模仿学习与强化学习：robotic(abstract)；分类 cs.LG

Comments Published in TMLR

2203.03986 2024-01-23 cs.RO math.OC 57%

Leveraging Randomized Smoothing for Optimal Control of Nonsmooth Dynamical Systems

Quentin Le Lidec, Fabian Schramm, Louis Montaut, Cordelia Schmid, Ivan Laptev, Justin Carpentier

专题命中模仿学习与强化学习：robotic(abstract)；分类 cs.RO

2107.00116 2024-01-17 cs.LG 57%

On the Benefits of Inducing Local Lipschitzness for Robust Generative Adversarial Imitation Learning

Farzan Memarian, Abolfazl Hashemi, Scott Niekum, Ufuk Topcu

专题命中模仿学习与强化学习：robotics(abstract)；分类 cs.LG

2401.07181 2024-01-17 cs.LG 57%

Reinforcement Learning from LLM Feedback to Counteract Goal Misgeneralization

Houda Nait El Barj, Theophile Sautory

专题命中模仿学习与强化学习：navigation(abstract)；分类 cs.LG

2401.01481 2024-01-04 cs.RO cs.MA 57%

Optimizing UAV-UGV Coalition Operations: A Hybrid Clustering and Multi-Agent Reinforcement Learning Approach for Path Planning in Obstructed Environment

Shamyo Brotee, Farhan Kabir, Md. Abdur Razzaque, Palash Roy, Md. Mamun-Or-Rashid, Md. Rafiul Hassan, Mohammad Mehedi Hassan

专题命中模仿学习与强化学习：navigation(abstract)；分类 cs.RO

2211.15542 2024-01-03 cs.LG 57%

Autonomous Assessment of Demonstration Sufficiency via Bayesian Inverse Reinforcement Learning

Tu Trinh, Haoyu Chen, Daniel S. Brown

专题命中模仿学习与强化学习：robotic(abstract)；分类 cs.LG

Comments Prior version appears in proceedings of AAAI FSS-22 Symposium "Lessons Learned for Autonomous Assessment of Machine Abilities (LLAAMA)". Current version appears in proceedings of HRI '24, March 11-14, 2024, Boulder, CO, USA

2312.15127 2023-12-27 cs.LG 57%

Gradient Shaping for Multi-Constraint Safe Reinforcement Learning

Yihang Yao, Zuxin Liu, Zhepeng Cen, Peide Huang, Tingnan Zhang, Wenhao Yu, Ding Zhao

专题命中模仿学习与强化学习：manipulation(abstract)；分类 cs.LG

2312.11374 2023-12-19 cs.RO 57%

Mastering Stacking of Diverse Shapes with Large-Scale Iterative Reinforcement Learning on Real Robots

Thomas Lampe, Abbas Abdolmaleki, Sarah Bechtle, Sandy H. Huang, Jost Tobias Springenberg, Michael Bloesch, Oliver Groth, Roland Hafner, Tim Hertweck, Michael Neunert, Markus Wulfmeier, Jingwei Zhang, Francesco Nori, Nicolas Heess, Martin Riedmiller

专题命中模仿学习与强化学习：manipulation(abstract)；分类 cs.RO

2312.05787 2023-12-12 cs.LG 57%

Efficient Sparse-Reward Goal-Conditioned Reinforcement Learning with a High Replay Ratio and Regularization

Takuya Hiraoka

专题命中模仿学习与强化学习：robotics(abstract)；分类 cs.LG

Comments Source code: https://github.com/TakuyaHiraoka/Efficient-SRGC-RL-with-a-High-RR-and-Regularization Demo video: https://drive.google.com/file/d/1UHd7JVPCwFLNFhy1QcycQfwU_nll_yII/view?usp=drive_link

2312.05465 2023-12-12 cs.LG cs.SY eess.SY 57%

On Task-Relevant Loss Functions in Meta-Reinforcement Learning and Online LQR

Jaeuk Shin, Giho Kim, Howon Lee, Joonho Han, Insoon Yang

专题命中模仿学习与强化学习：robotic(abstract)；分类 cs.LG

2007.00245 2023-12-11 cs.RO 57%

Fighting Failures with FIRE: Failure Identification to Reduce Expert Burden in Intervention-Based Learning

Trevor Ablett, Filip Marić, Jonathan Kelly

专题命中模仿学习与强化学习：manipulation(abstract)；分类 cs.RO

Comments Technical Report STARS-2020-001, University of Toronto Institute for Aerospace Studies (14 pages, 7 figures)

2306.02551 2023-12-08 cs.RO 57%

Conformal Predictive Safety Filter for RL Controllers in Dynamic Environments

Kegan J. Strawn, Nora Ayanian, Lars Lindemann

专题命中模仿学习与强化学习：navigation(abstract)；分类 cs.RO

2311.16838 2023-11-29 cs.RO 57%

Increasing Transparency of Reinforcement Learning using Shielding for Human Preferences and Explanations

Georgios Angelopoulos, Luigi Mangiacapra, Alessandra Rossi, Claudia Di Napoli, Silvia Rossi

专题命中模仿学习与强化学习：robotic(abstract)；分类 cs.RO

2305.15363 2023-11-28 cs.LG 57%

Inverse Preference Learning: Preference-based RL without a Reward Function

Joey Hejna, Dorsa Sadigh

专题命中模仿学习与强化学习：robotics(abstract)；分类 cs.LG

Comments Updated for NeurIPS 2023 Acceptance

2311.13714 2023-11-27 cs.RO cs.MA cs.SY eess.SY math.OC 57%

Learning Safe Control for Multi-Robot Systems: Methods, Verification, and Open Challenges

Kunal Garg, Songyuan Zhang, Oswin So, Charles Dawson, Chuchu Fan

专题命中模仿学习与强化学习：robotic(abstract)；分类 cs.RO

Comments Submitted to Annual Reviews in Control

2212.08131 2023-11-23 cs.LG 57%

Bridging the Gap Between Offline and Online Reinforcement Learning Evaluation Methodologies

Shivakanth Sujit, Pedro H. M. Braga, Jorg Bornschein, Samira Ebrahimi Kahou

专题命中模仿学习与强化学习：robotics(abstract)；分类 cs.LG

Comments TMLR 2023

1. 模仿学习与强化学习 4134 篇

Bridging the Gap: Regularized Reinforcement Learning for Improved Classical Motion Planning with Safety Modules

Decomposing Control Lyapunov Functions for Efficient Reinforcement Learning

Causality from Bottom to Top: A Survey

Recent Developments in Machine Learning Methods for Stochastic Control and Games

Enhancing Task Performance of Learned Simplified Models via Reinforcement Learning

Sample Efficient Myopic Exploration Through Multitask Reinforcement Learning with Diverse Tasks

An Open-Loop Baseline for Reinforcement Learning Locomotion Tasks

Continuous Mean-Zero Disagreement-Regularized Imitation Learning (CMZ-DRIL)

RELAX: Reinforcement Learning Enabled 2D-LiDAR Autonomous System for Parsimonious UAVs

Pretty darn good control: when are approximate solutions better than approximate models

Learning Decentralized Partially Observable Mean Field Control for Artificial Collective Behavior

Reward Bound for Behavioral Guarantee of Model-based Planning Agents

Informativeness of Reward Functions in Reinforcement Learning

TartanDrive 2.0: More Modalities and Better Infrastructure to Further Self-Supervised Learning Research in Off-Road Driving Tasks

Multi-Horizon Representations with Hierarchical Forward Models for Reinforcement Learning

Leveraging Randomized Smoothing for Optimal Control of Nonsmooth Dynamical Systems

On the Benefits of Inducing Local Lipschitzness for Robust Generative Adversarial Imitation Learning

Reinforcement Learning from LLM Feedback to Counteract Goal Misgeneralization

Optimizing UAV-UGV Coalition Operations: A Hybrid Clustering and Multi-Agent Reinforcement Learning Approach for Path Planning in Obstructed Environment

Autonomous Assessment of Demonstration Sufficiency via Bayesian Inverse Reinforcement Learning

Gradient Shaping for Multi-Constraint Safe Reinforcement Learning

Mastering Stacking of Diverse Shapes with Large-Scale Iterative Reinforcement Learning on Real Robots

Efficient Sparse-Reward Goal-Conditioned Reinforcement Learning with a High Replay Ratio and Regularization

On Task-Relevant Loss Functions in Meta-Reinforcement Learning and Online LQR

Fighting Failures with FIRE: Failure Identification to Reduce Expert Burden in Intervention-Based Learning

Conformal Predictive Safety Filter for RL Controllers in Dynamic Environments

Increasing Transparency of Reinforcement Learning using Shielding for Human Preferences and Explanations

Inverse Preference Learning: Preference-based RL without a Reward Function

Learning Safe Control for Multi-Robot Systems: Methods, Verification, and Open Challenges

Bridging the Gap Between Offline and Online Reinforcement Learning Evaluation Methodologies