paper-with-me

Papers

Closed-loop Teaching via Demonstrations to Improve Policy Transparency

2024-04-01 · Michael S. Lee, Reid Simmons, Henny Admoni

Demonstrations are a powerful way of increasing the transparency of AI policies. Though informative demonstrations may be selected a priori through the machine teaching paradigm, student learning may deviate from the preselected curriculum in situ. This paper thus explores augmenting a curriculum with a closed-loop teaching framework inspired by principles from the education literature, such as the zone of proximal development and the testing effect. We utilize tests accordingly to close to the loop and maintain a novel particle filter model of human beliefs throughout the learning process, allowing us to provide demonstrations that are targeted to the human's current understanding in real time. A user study finds that our proposed closed-loop teaching framework reduces the regret in human test responses by 43% over a baseline.

📄 PDF Abstract BibTeX arXiv:2406.11850

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Learning Lipschitz Feedback Policies from Expert Demonstrations: Closed-Loop Guarantees, Generalization and Robustness

2021-03-30 · Abed AlRahman Al Makdah, Vishaal Krishnan, Fabio Pasqualetti

In this work, we propose a framework to learn feedback control policies with guarantees on closed-loop generalization and adversarial robustness. These policies are learned directly from expert demonstrations, contained …

Adversarial RobustnessImitation Learning

RoaD: Rollouts as Demonstrations for Closed-Loop Supervised Fine-Tuning of Autonomous Driving Policies

2025-12-01 · Guillermo Garcia-Cobo, Maximilian Igl, Peter Karkus, Zhejun Zhang 외 arxiv

Autonomous driving policies are typically trained via open-loop behavior cloning of human demonstrations. However, such policies suffer from covariate shift when deployed in closed loop, leading to compounding errors. We…

Reinforcement LearningAutonomous Driving

OKAMI: Teaching Humanoid Robots Manipulation Skills through Single Video Imitation

2024-10-15 · Jinhan Li, Yifeng Zhu, Yuqi Xie, Zhenyu Jiang 외

We study the problem of teaching humanoid robots manipulation skills by imitating from single video demonstrations. We introduce OKAMI, a method that generates a manipulation plan from a single RGB-D video and derives a …

Machine Teaching for Inverse Reinforcement Learning: Algorithms and Applications

2018-05-20 · Daniel S. Brown, Scott Niekum

Inverse reinforcement learning (IRL) infers a reward function from demonstrations, allowing for policy improvement and generalization. However, despite much recent interest in IRL, little work has been done to understand…

Decision Makingreinforcement-learningReinforcement LearningReinforcement Learning (RL)+1

From Imitation to Refinement -- Residual RL for Precise Assembly

2024-07-23 · Lars Ankile, Anthony Simeonov, Idan Shenfeld, Marcel Torne 외

Recent advances in Behavior Cloning (BC) have made it easy to teach robots new tasks. However, we find that the ease of teaching comes at the cost of unreliable performance that saturates with increasing data for tasks r…

ChunkingPolicy Gradient MethodsReinforcement Learning (RL)