机器人 / 具身智能 - arXivDaily 专题

2310.19668 2024-02-15 cs.LG cs.CV 62%

DrM: Mastering Visual Reinforcement Learning through Dormant Ratio Minimization

Guowei Xu, Ruijie Zheng, Yongyuan Liang, Xiyao Wang, Zhecheng Yuan, Tianying Ji, Yu Luo, Xiaoyu Liu, Jiaxin Yuan, Pu Hua, Shuzhen Li, Yanjie Ze, Hal Daumé, Furong Huang, Huazhe Xu

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

Comments Accepted at The Twelfth International Conference on Learning Representations (ICLR 2024)

2402.07412 2024-02-13 cs.LG cs.AI 62%

Auxiliary Reward Generation with Transition Distance Representation Learning

Siyuan Li, Shijie Han, Yingnan Zhao, By Liang, Peng Liu

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

2402.06023 2024-02-12 cs.LG cs.AI cs.GT 62%

Decision Theory-Guided Deep Reinforcement Learning for Fast Learning

Zelin Wan, Jin-Hee Cho, Mu Zhu, Ahmed H. Anwar, Charles Kamhoua, Munindar P. Singh

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

2402.03072 2024-02-06 q-bio.NC cs.AI cs.LG 62%

Learning to Abstract Visuomotor Mappings using Meta-Reinforcement Learning

Carlos A. Velazquez-Vargas, Isaac Ray Christian, Jordan A. Taylor, Sreejan Kumar

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

2305.13795 2024-01-31 cs.LG cs.AI 62%

Proximal Policy Gradient Arborescence for Quality Diversity Reinforcement Learning

Sumeet Batra, Bryon Tjanaka, Matthew C. Fontaine, Aleksei Petrenko, Stefanos Nikolaidis, Gaurav Sukhatme

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

Comments Accepted as a spotlight paper at ICLR 2024

2211.06236 2024-01-30 cs.LG cs.AI 62%

Efficient Deep Reinforcement Learning with Predictive Processing Proximal Policy Optimization

Burcu Küçükoğlu, Walraaf Borkent, Bodo Rueckauer, Nasir Ahmad, Umut Güçlü, Marcel van Gerven

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

Comments 24 pages, 8 figures

2401.12975 2024-01-24 cs.CV cs.AI cs.CL 62%

HAZARD Challenge: Embodied Decision Making in Dynamically Changing Environments

Qinhong Zhou, Sunli Chen, Yisong Wang, Haozhe Xu, Weihua Du, Hongxin Zhang, Yilun Du, Joshua B. Tenenbaum, Chuang Gan

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

Comments ICLR 2024. The first two authors contributed equally to this work

2311.10309 2024-01-24 cs.LG cs.RO 62%

Imagination-Augmented Hierarchical Reinforcement Learning for Safe and Interactive Autonomous Driving in Urban Environments

Sang-Hyun Lee, Yoonjae Jung, Seung-Woo Seo

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

Comments 15 pages, 9 figures; corrected typos, added references, revised experiments (results unchanged)

2305.04073 2024-01-23 cs.AI cs.LG 62%

Explaining RL Decisions with Trajectories

Shripad Vilasrao Deshmukh, Arpan Dasgupta, Balaji Krishnamurthy, Nan Jiang, Chirag Agarwal, Georgios Theocharous, Jayakumar Subramanian

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

Comments Published at International Conference on Learning Representations (ICLR), 2023

2311.13326 2024-01-17 cs.LG cs.AI q-fin.PM 62%

Curriculum Learning and Imitation Learning for Model-free Control on Financial Time-series

Woosung Koh, Insu Choi, Yuntae Jang, Gimin Kang, Woo Chang Kim

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

Comments AAAI 2024 AI4TS Workshop Oral

2312.17168 2023-12-29 cs.LG cs.AI 62%

Can Active Sampling Reduce Causal Confusion in Offline Reinforcement Learning?

Gunshi Gupta, Tim G. J. Rudner, Rowan Thomas McAllister, Adrien Gaidon, Yarin Gal

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

Comments Published in Proceedings of the 2nd Conference on Causal Learning and Reasoning (CLeaR 2021)

2312.16365 2023-12-29 cs.LG cs.AI stat.ML 62%

Active Third-Person Imitation Learning

Timo Klein, Susanna Weinberger, Adish Singla, Sebastian Tschiatschek

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

2301.10923 2023-12-27 cs.LG cs.AI 62%

Trust Region-Based Safe Distributional Reinforcement Learning for Multiple Constraints

Dohyeong Kim, Kyungjae Lee, Songhwai Oh

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

Comments 32 pages, Accepted at NeurIPS 2023

2312.10802 2023-12-19 cs.LG cs.AI 62%

GO-DICE: Goal-Conditioned Option-Aware Offline Imitation Learning via Stationary Distribution Correction Estimation

Abhinav Jain, Vaibhav Unhelkar

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

Comments Extended version of an identically-titled paper accepted at AAAI 2024

2312.10328 2023-12-19 cs.RO cs.LG cs.LO 62%

Deriving Rewards for Reinforcement Learning from Symbolic Behaviour Descriptions of Bipedal Walking

Daniel Harnack, Christoph Lüth, Lukas Gross, Shivesh Kumar, Frank Kirchner

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

Comments To appear in 62nd IEEE Conference on Decision and Control (CDC). For supplemental material, see here https://dfki-ric-underactuated-lab.github.io/orthant_rewards_biped_rl/

2312.10289 2023-12-19 cs.LG cs.AI cs.SY eess.SY 62%

Active Reinforcement Learning for Robust Building Control

Doseok Jang, Larry Yan, Lucas Spangher, Costas Spanos

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

2312.09906 2023-12-18 cs.RO cs.AI 62%

Sample-Efficient Learning to Solve a Real-World Labyrinth Game Using Data-Augmented Model-Based Reinforcement Learning

Thomas Bi, Raffaello D'Andrea

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

2307.08875 2023-12-12 cs.LG cs.RO math.OC 62%

Natural Actor-Critic for Robust Reinforcement Learning with Function Approximation

Ruida Zhou, Tao Liu, Min Cheng, Dileep Kalathil, P. R. Kumar, Chao Tian

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

Comments Neurips 2023

2306.01804 2023-12-12 cs.LG cs.AI 62%

Extracting Reward Functions from Diffusion Models

Felipe Nuti, Tim Franzmeyer, João F. Henriques

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

Comments NeurIPS 2023

2109.08642 2023-12-12 cs.RO cs.AI 62%

POAR: Efficient Policy Optimization via Online Abstract State Representation Learning

Zhaorun Chen, Siqi Fan, Yuan Tan, Liang Gong, Binhao Chen, Te Sun, David Filliat, Natalia Díaz-Rodríguez, Chengliang Liu

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

Comments 19 pages

2312.00966 2023-12-11 cs.LG cs.AI 62%

Spectral Temporal Contrastive Learning

Sacha Morin, Somjit Nath, Samira Ebrahimi Kahou, Guy Wolf

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

Comments Accepted to Self-Supervised Learning - Theory and Practice, NeurIPS Workshop, 2023

2312.02649 2023-12-06 cs.RO cs.LG 62%

A Q-learning approach to the continuous control problem of robot inverted pendulum balancing

Mohammad Safeea, Pedro Neto

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

2207.02016 2023-12-06 cs.LG cs.AI cs.SY eess.SY 62%

Robust Reinforcement Learning in Continuous Control Tasks with Uncertainty Set Regularization

Yuan Zhang, Jianhong Wang, Joschka Boedecker

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

Comments Accepted at CoRL 2023

2312.01249 2023-12-05 cs.RO cs.AI cs.SY eess.SY 62%

A Multifidelity Sim-to-Real Pipeline for Verifiable and Compositional Reinforcement Learning

Cyrus Neary, Christian Ellis, Aryaman Singh Samyal, Craig Lennon, Ufuk Topcu

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

2310.19308 2023-12-05 cs.LG cs.AI 62%

Free from Bellman Completeness: Trajectory Stitching via Model-based Return-conditioned Supervised Learning

Zhaoyi Zhou, Chuning Zhu, Runlong Zhou, Qiwen Cui, Abhishek Gupta, Simon Shaolei Du

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

2307.10936 2023-12-05 cs.AI cs.LG 62%

PASTA: Pretrained Action-State Transformer Agents

Raphael Boige, Yannis Flet-Berliac, Arthur Flajolet, Guillaume Richard, Thomas Pierrot

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

2311.09233 2023-11-17 cs.LG cs.GR cs.RO 62%

Neural Packing: from Visual Sensing to Reinforcement Learning

Juzhan Xu, Minglun Gong, Hao Zhang, Hui Huang, Ruizhen Hu

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

2311.03669 2023-11-08 cs.LG cs.AI cs.SY eess.SY 62%

Stable Modular Control via Contraction Theory for Reinforcement Learning

Bing Song, Jean-Jacques Slotine, Quang-Cuong Pham

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

2103.05147 2023-11-03 cs.LG cs.AI 62%

Model-free Policy Learning with Reward Gradients

Qingfeng Lan, Samuele Tosatto, Homayoon Farrahi, A. Rupam Mahmood

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

Comments AISTATS 2022 camera-ready (fixed a bug)

2311.00267 2023-11-02 cs.LG cs.AI 62%

Rethinking Decision Transformer via Hierarchical Reinforcement Learning

Yi Ma, Chenjun Xiao, Hebin Liang, Jianye Hao

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

1. 模仿学习与强化学习 4131 篇

DrM: Mastering Visual Reinforcement Learning through Dormant Ratio Minimization

Auxiliary Reward Generation with Transition Distance Representation Learning

Decision Theory-Guided Deep Reinforcement Learning for Fast Learning

Learning to Abstract Visuomotor Mappings using Meta-Reinforcement Learning

Proximal Policy Gradient Arborescence for Quality Diversity Reinforcement Learning

Efficient Deep Reinforcement Learning with Predictive Processing Proximal Policy Optimization

HAZARD Challenge: Embodied Decision Making in Dynamically Changing Environments

Imagination-Augmented Hierarchical Reinforcement Learning for Safe and Interactive Autonomous Driving in Urban Environments

Explaining RL Decisions with Trajectories

Curriculum Learning and Imitation Learning for Model-free Control on Financial Time-series

Can Active Sampling Reduce Causal Confusion in Offline Reinforcement Learning?

Active Third-Person Imitation Learning

Trust Region-Based Safe Distributional Reinforcement Learning for Multiple Constraints

GO-DICE: Goal-Conditioned Option-Aware Offline Imitation Learning via Stationary Distribution Correction Estimation

Deriving Rewards for Reinforcement Learning from Symbolic Behaviour Descriptions of Bipedal Walking

Active Reinforcement Learning for Robust Building Control

Sample-Efficient Learning to Solve a Real-World Labyrinth Game Using Data-Augmented Model-Based Reinforcement Learning

Natural Actor-Critic for Robust Reinforcement Learning with Function Approximation

Extracting Reward Functions from Diffusion Models

POAR: Efficient Policy Optimization via Online Abstract State Representation Learning

Spectral Temporal Contrastive Learning

A Q-learning approach to the continuous control problem of robot inverted pendulum balancing

Robust Reinforcement Learning in Continuous Control Tasks with Uncertainty Set Regularization

A Multifidelity Sim-to-Real Pipeline for Verifiable and Compositional Reinforcement Learning

Free from Bellman Completeness: Trajectory Stitching via Model-based Return-conditioned Supervised Learning

PASTA: Pretrained Action-State Transformer Agents

Neural Packing: from Visual Sensing to Reinforcement Learning

Stable Modular Control via Contraction Theory for Reinforcement Learning

Model-free Policy Learning with Reward Gradients

Rethinking Decision Transformer via Hierarchical Reinforcement Learning