paper-with-me

홈 › Papers

Optimizing Neurorobot Policy under Limited Demonstration Data through Preference Regret

2026-04-04 · Viet Dung Nguyen, Yuhang Song, Anh Nguyen, Jamison Heard, Reynold Bailey, Alexander Ororbia arxiv

Robot reinforcement learning from demonstrations (RLfD) assumes that expert data is abundant; this is usually unrealistic in the real world given data scarcity as well as high collection cost. Furthermore, imitation learning algorithms assume that the data is independently and identically distributed, which ultimately results in poorer performance as gradual errors emerge and compound within test-time trajectories. We address these issues by introducing the "master your own expertise" (MYOE) framework, a self-imitation framework that enables robotic agents to learn complex behaviors from limited demonstration data samples. Inspired by human perception and action, we propose and design what we call the queryable mixture-of-preferences state space model (QMoP-SSM), which estimates the desired goal at every time step. These desired goals are used in computing the "preference regret", which is used to optimize the robot control policy. Our experiments demonstrate the robustness, adaptability, and out-of-sample performance of our agent compared to other state-of-the-art RLfD schemes. The GitHub repository that supports this work can be found at: https://github.com/rxng8/neurorobot-preference-regret-learning.

📄 PDF Abstract BibTeX arXiv:2604.03523

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

Reward Learning from Suboptimal Demonstrations with Applications in Surgical Electrocautery

2024-04-10 · Zohre Karimi, Shing-Hei Ho, Bao Thach, Alan Kuntz 외

Automating robotic surgery via learning from demonstration (LfD) techniques is extremely challenging. This is because surgical tasks often involve sequential decision-making processes with complex interactions of physica…

Decision MakingImitation LearningReinforcement Learning (RL)Sequential Decision Making

Integrating Behavior Cloning and Reinforcement Learning for Improved Performance in Dense and Sparse Reward Environments

2019-10-09 · Vinicius G. Goecks, Gregory M. Gremillion, Vernon J. Lawhern, John Valasek 외

This paper investigates how to efficiently transition and update policies, trained initially with demonstrations, using off-policy actor-critic reinforcement learning. It is well-known that techniques based on Learning f…

Q-Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Robot Policy Transfer with Online Demonstrations: An Active Reinforcement Learning Approach

2025-03-17 · Muhan Hou, Koen Hindriks, A. E. Eiben, Kim Baraka

Transfer Learning (TL) is a powerful tool that enables robots to transfer learned policies across different environments, tasks, or embodiments. To further facilitate this process, efforts have been made to combine it wi…

Transfer Learning

A Neurorobotics Approach to Behaviour Selection based on Human Activity Recognition

2021-07-27 · Caetano M. Ranieri, Renan C. Moioli, Patricia A. Vargas, Roseli A. F. Romero

Behaviour selection has been an active research topic for robotics, in particular in the field of human-robot interaction. For a robot to interact effectively and autonomously with humans, the coupling between techniques…

Activity RecognitionDecision MakingHuman Activity Recognition

D-REX: Differentiable Real-to-Sim-to-Real Engine for Learning Dexterous Grasping

2026-03-01 · Haozhe Lou, Mingtong Zhang, Haoran Geng, Hanyang Zhou 외 arxiv

Simulation provides a cost-effective and flexible platform for data generation and policy learning to develop robotic systems. However, bridging the gap between simulation and real-world dynamics remains a significant ch…