paper-with-me

Papers

Learning Options from Demonstration using Skill Segmentation

2020-01-19 · Matthew Cockcroft, Shahil Mawjee, Steven James, Pravesh Ranchod

We present a method for learning options from segmented demonstration trajectories. The trajectories are first segmented into skills using nonparametric Bayesian clustering and a reward function for each segment is then learned using inverse reinforcement learning. From this, a set of inferred trajectories for the demonstration are generated. Option initiation sets and termination conditions are learned from these trajectories using the one-class support vector machine clustering algorithm. We demonstrate our method in the four rooms domain, where an agent is able to autonomously discover usable options from human demonstration. Our results show that these inferred options can then be used to improve learning and planning.

📄 PDF Abstract BibTeX arXiv:2001.06793

Code (0)

등록된 구현이 없습니다.

Tasks

Clusteringreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Inducing Reusable Skills From Demonstrations with Option-Controller Network

2021-09-29 · Siyuan Zhou, Yikang Shen, Yuchen Lu, Aaron Courville 외

Humans can decompose previous experiences into skills and reuse them to enable fast learning in the future. Inspired by this process, we propose a new model called Option-Controller Network (OCN), which is a bi-level rec…

Learning Robot Skills with Temporal Variational Inference

2020-06-29 · ICML 2020 1 · Tanmay Shankar, Abhinav Gupta

In this paper, we address the discovery of robotic options from demonstrations in an unsupervised manner. Specifically, we present a framework to jointly learn low-level control policies and higher-level policies of how …

Variational Inference

Weakly-Supervised Trajectory Segmentation for Learning Reusable Skills

2019-09-25 · Parsa Mahmoudieh, Trevor Darrell, Deepak Pathak

Learning useful and reusable skill, or sub-task primitives, is a long-standing problem in sensorimotor control. This is challenging because it's hard to define what constitutes a useful skill. Instead of direct manual su…

Multiple Instance LearningSegmentation

OptionZero: Planning with Learned Options

2025-02-23 · Po-Wei Huang, Pei-Chiun Peng, Hung Guei, Ti-Rong Wu

Planning with options -- a sequence of primitive actions -- has been shown effective in reinforcement learning within complex environments. Previous studies have focused on planning with predefined options or learned opt…

Atari Games

Adversarial Option-Aware Hierarchical Imitation Learning

2021-06-10 · Mingxuan Jing, Wenbing Huang, Fuchun Sun, Xiaojian Ma 외

It has been a challenge to learning skills for an agent from long-horizon unannotated demonstrations. Existing approaches like Hierarchical Imitation Learning(HIL) are prone to compounding errors or suboptimal solutions.…

Imitation Learning