Constructing Skill Trees for Reinforcement Learning Agents from Demonstration Trajectories

2010-12-01 · NeurIPS 2010 12 · George Konidaris, Scott Kuindersma, Roderic Grupen, Andrew G. Barto

We introduce CST, an algorithm for constructing skill trees from demonstration trajectories in continuous reinforcement learning domains. CST uses a changepoint detection method to segment each trajectory into a skill chain by detecting a change of appropriate abstraction, or that a segment is too complex to model as a single skill. The skill chains from each trajectory are then merged to form a skill tree. We demonstrate that CST constructs an appropriate skill tree that can be further refined through learning in a challenging continuous domain, and that it can be used to segment demonstration trajectories on a mobile manipulator into chains of skills where each skill is assigned an appropriate abstraction.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Boosting Reinforcement Learning and Planning with Demonstrations: A Survey

2023-03-23 · Tongzhou Mu, Hao Su

Although reinforcement learning has seen tremendous success recently, this kind of trial-and-error learning can be impractical or inefficient in complex environments. The use of demonstrations, on the other hand, enables…

Decision Making reinforcement-learning Reinforcement Learning Sequential Decision Making+1

Learning Complicated Manipulation Skills via Deterministic Policy with Limited Demonstrations

2023-03-29 · Liu Haofeng, Chen Yiwen, Tan Jiayi, Marcelo H Ang

Combined with demonstrations, deep reinforcement learning can efficiently develop policies for manipulators. However, it takes time to collect sufficient high-quality demonstrations in practice. And human demonstrations …

Deep Reinforcement Learning MuJoCo reinforcement-learning Reinforcement Learning

Skill Reinforcement Learning and Planning for Open-World Long-Horizon Tasks

2023-03-29 · Haoqi Yuan, Chi Zhang, Hongcheng Wang, Feiyang Xie 외

We study building multi-task agents in open-world environments. Without human demonstrations, learning to accomplish long-horizon tasks in a large open-world environment with reinforcement learning (RL) is extremely inef…

Minecraft Multi-Task Learning reinforcement-learning Reinforcement Learning (RL)

Learning Safety Constraints From Demonstration Using One-Class Decision Trees

2023-12-14 · Mattijs Baert, Sam Leroux, Pieter Simoens

The alignment of autonomous agents with human values is a pivotal challenge when deploying these agents within physical environments, where safety is an important concern. However, defining the agent's objective as a rew…

Skill-Enhanced Reinforcement Learning Acceleration from Demonstrations

2024-12-09 · Hanping Zhang, Yuhong Guo

Learning from Demonstration (LfD) aims to facilitate rapid Reinforcement Learning (RL) by leveraging expert demonstrations to pre-train the RL agent. However, the limited availability of expert demonstration data often h…