Reinforcement Learning for Pivoting Task

In this work we propose an approach to learn a robust policy for solving the pivoting task. Recently, several model-free continuous control algorithms were shown to learn successful policies withou ...

cs.RO cs.LG Computer Science

View graph Source

Paper

References (19)

01Sim-to-Real Robot Learning from Pixels with Progressive NetsAndrei A. Rusu, Matej Vecerík, Thomas Rothörl et al.2016 · Conference on Robot Learning · 568 citations In Library

02OpenAI GymGreg Brockman, Vicki Cheung, Ludwig Pettersson et al.2016 · arXiv.org · 5.6k citations In Library

03Adaptive control for pivoting with visual and tactile feedbackFrancisco E. Vina, Y. Karayiannidis, Christian Smith et al.2016 · IEEE International Conference on Robotics and Automation · 74 citations

04Swing-up regrasping algorithm using energy controlA. Sintov, Amir Shapiro2016 · IEEE International Conference on Robotics and Automation · 21 citations

05Benchmarking Deep Reinforcement Learning for Continuous ControlYan Duan, Xi Chen, Rein Houthooft et al.2016 · International Conference on Machine Learning · 1.8k citations In Library

06In-hand manipulation using gravity and controlled slipFrancisco E. Vina, Y. Karayiannidis, Karl Pauwels et al.2015 · IEEE/RJS International Conference on Intelligent RObots and Systems · 48 citations

07A two-phase gripper to reorient and graspNikhil Chavan Dafle, M. T. Mason, H. Staab et al.2015 · 2015 IEEE International Conference on Automation Science and Engineering (CASE) · 46 citations

08Continuous control with deep reinforcement learningT. Lillicrap, Jonathan J. Hunt, A. Pritzel et al.2015 · International Conference on Learning Representations · 16k citations In Library

09A general framework for open-loop pivotingA. Holladay, R. Paolini, M. T. Mason2015 · IEEE International Conference on Robotics and Automation · 54 citations

10Trust Region Policy OptimizationJohn Schulman, S. Levine, P. Abbeel et al.2015 · International Conference on Machine Learning · 8.2k citations In Library

11Learning Neural Network Policies with Guided Policy Search under Unknown DynamicsS. Levine, P. Abbeel2014 · Neural Information Processing Systems · 528 citations

12Extrinsic dexterity: In-hand manipulation with external forcesNikhil Chavan Dafle, Alberto Rodriguez, R. Paolini et al.2014 · IEEE International Conference on Robotics and Automation · 314 citations

Scroll for more · 7 remaining

Similar papers

Learning Continuous Control Actions for Robotic Grasping with Reinforcement LearningAsad Ali Shahid, Loris Roveda, Dario Piga et al.2020 · IEEE International Conference on Systems, Man and Cybernetics · 44 citations In Library

A Pontryagin Perspective on Reinforcement LearningOnno Eberhard, Claire Vernade, Michael Muehlebach2024 · Conference on Learning for Dynamics & Control · 11 citations In Library

Controlling Agents by Constrained Policy UpdatesMónika Farsang, Luca Szegletes2021 · SYSTEM THEORY CONTROL AND COMPUTING JOURNAL In Library

Continuous control actions learning and adaptation for robotic manipulation through reinforcement learningAsad Ali Shahid, Dario Piga, Francesco Braghin et al.2022 · Autonomous Robots · 61 citations In Library

Addressing Action Oscillations through Learning Policy InertiaChen Chen, Hongyao Tang, Jianye Hao et al.2021 · arXiv (Cornell University) · 28 citations In Library

Reinforcement Learning Control of Robotic Knee with Human in the Loop by Flexible Policy IterationXiang Gao, J. Si, Yue Wen et al.2020 · IEEE Transactions on Neural Networks and Learning Systems · 38 citations In Library

Reinforcement-Learning-Driven Policy Optimization and Control for Autonomous Agents Marcus Aurelius, Noah Russo, Noah P Grayson2026 · Global Media and Social Sciences Research Journal In Library

Addressing Action Oscillations through Learning Policy InertiaChen Chen, Hongyao Tang, Jianye Hao et al.2021 · Proceedings of the AAAI Conference on Artificial Intelligence In Library

Model-Based Reinforcement Learning via Proximal Policy OptimizationYuewen Sun, Xin Yuan, Wenzhang Liu et al.2019 · ACM Cloud and Autonomic Computing Conference · 22 citations In Library

Intelligent Control of a Quadrotor with Proximal Policy Optimization Reinforcement LearningGuilherme Cano Lopes, M. Ferreira, A. S. Simões et al.2018 · 2018 Latin American Robotic Symposium, 2018 Brazilian Symposium on Robotics (SBR) and 2018 Workshop on Robotics in Education (WRE) · 55 citations In Library

Patents near this paper

ARTIFICIAL INTELLIGENCE SYSTEM FOR EFFICIENTLY LEARNING ROBOTIC CONTROL POLICIESUS 10,926,408 · AMAZON TECHNOLOGIES, INC. · 2021 INVERSE REINFORCEMENT LEARNING WITH MODEL PREDICTIVE CONTROLUS 11,579,575 · BAIDU USA, LLC · 2023 DEEP REINFORCEMENT LEARNING FOR ROBOTIC MANIPULATIONUS 11,400,587 · GOOGLE INC. · 2022 CLOSED LOOP MODEL-BASED ACTION LEARNING WITH MODEL-FREE INVERSE REINFORCEMENT LEARNINGUS 11,468,334 · INTERNATIONAL BUSINESS MACHINES CORPORATION · 2022 ROBOT CONTROL POLICY DETERMINATION THROUGH CONSTRAINED OPTIMIZATION FOR SMOOTH CONTINUOUS CONTROLUS 10,786,900 · DEEPMIND TECHNOLOGIES LIMITED · 2020

Source of record

arXiv