Meta Reinforcement Learning for Fast Adaptation of Hierarchical Policies

2021-05-21 · NeurIPS 2021 12 · David Kuric, Herke van Hoof

Hierarchical methods have the potential to allow reinforcement learning to scale to larger environments. Decomposing a task into transferable components, however, remains a challenging problem. In this paper, we propose a meta-learning approach for learning such a decomposition within the options framework. We formulate the objective as a bi-level optimization problem in which sub-policies and their terminations should facilitate fast learning on a family of tasks. Once such a set of options is obtained, it can then be used in new tasks where only the sequencing of options needs to be chosen. Our formalism tends to result in options where fewer decisions are needed to solve such new tasks. Experimentally, we show that our method is able to learn transferable components which accelerate learning and performs better than existing methods developed for this setting in the challenging ant maze locomotion task.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Meta-LearningMeta Reinforcement Learningreinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Hierarchical Meta-Reinforcement Learning via Automated Macro-Action Discovery

2024-12-16 · Minjae Cho, Chuangchuang Sun

Meta-Reinforcement Learning (Meta-RL) enables fast adaptation to new testing tasks. Despite recent advancements, it is still challenging to learn performant policies across multiple complex and high-dimensional tasks. To…

Meta Reinforcement Learning reinforcement-learning Reinforcement Learning

Meta-Learning Integration in Hierarchical Reinforcement Learning for Advanced Task Complexity

2024-10-10 · Arash Khajooeinejad, Masoumeh Chapariniya

Hierarchical Reinforcement Learning (HRL) effectively tackles complex tasks by decomposing them into structured policies. However, HRL agents often face challenges with efficient exploration and rapid adaptation. To addr…

Efficient Exploration Hierarchical Reinforcement Learning Meta-Learning

Efficient Meta Reinforcement Learning for Preference-based Fast Adaptation

2022-11-20 · Zhizhou Ren, Anji Liu, Yitao Liang, Jian Peng 외

Learning new task-specific skills from a few trials is a fundamental challenge for artificial intelligence. Meta reinforcement learning (meta-RL) tackles this problem by learning transferable policies that support few-sh…

Meta Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Meta Hierarchical Reinforcement Learning for Scalable Resource Management in O-RAN

2025-12-08 · Fatemeh Lotfi, Fatemeh Afghah arxiv

The increasing complexity of modern applications demands wireless networks capable of real time adaptability and efficient resource management. The Open Radio Access Network (O-RAN) architecture, with its RAN Intelligent…

Hierarchical Reinforcement Learning

Quick Learner Automated Vehicle Adapting its Roadmanship to Varying Traffic Cultures with Meta Reinforcement Learning

2021-04-18 · Songan Zhang, Lu Wen, Huei Peng, H. Eric Tseng

It is essential for an automated vehicle in the field to perform discretionary lane changes with appropriate roadmanship - driving safely and efficiently without annoying or endangering other road users - under a wide ra…

Deep Reinforcement Learning Meta Reinforcement Learning reinforcement-learning Reinforcement Learning+1