Hierarchical Skills for Efficient Exploration

2021/10/20 by Jonas Gehring, Gehring, Jonas, Gabriel Synnaeve +5 · 3 citations
Computer Science · Engineering · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Multimodal Machine Learning Applications #Reinforcement Learning in Robotics #Robot Manipulation and Learning #Robotics (cs.RO)

paper · pdf · doi:10.48550/arxiv.2110.10809

openalex publication_date 2021/10/20 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

In reinforcement learning, pre-trained low-level skills have the potential to greatly facilitate exploration. However, prior knowledge of the downstream task is required to strike the right balance between generality (fine-grained control) and specificity (faster learning) in skill design. In previous work on continuous control, the sensitivity of methods to this trade-off has not been addressed explicitly, as locomotion provides a suitable prior for navigation tasks, which have been of foremost interest. In this work, we analyze this trade-off for low-level policy pre-training with a new benchmark suite of diverse, sparse-reward tasks for bipedal robots. We alleviate the need for prior knowledge by proposing a hierarchical skill learning framework that acquires skills of varying complexity in an unsupervised manner. For utilization on downstream tasks, we present a three-layered hierarchical learning algorithm to automatically trade off between general and specific skills as required by the respective task. In our experiments, we show that our approach performs this trade-off effectively and achieves better results than current state-of-the-art methods for end- to-end hierarchical reinforcement learning and unsupervised skill discovery. Code and videos are available at https://facebookresearch.github.io/hsd3 .

Citations

• Swing-twist decomposition in Clifford algebra
• Between MDPs and semi-MDPs: A framework for temporal abstraction in reinforcement learning
• #Exploration: A Study of Count-Based Exploration for Deep Reinforcement\n Learning
• FeUdal Networks for Hierarchical Reinforcement Learning
• Data-Efficient Hierarchical Reinforcement Learning
• Soft Actor-Critic Algorithms and Applications
• Why Does Hierarchy (Sometimes) Work So Well in Reinforcement Learning?
• Discrete and Continuous Action Representation for Practical RL in Video Games
• Hierarchical Reinforcement Learning By Discovering Intrinsic Options

Cited by

• Goal Discovery with Causal Capacity for Efficient Reinforcement Learning
• Hierarchical Multi-Agent Reinforcement Learning with Control Barrier Functions for Safety-Critical Autonomous Systems
• Reinforcement Learning with Action Chunking

Related

• Hierarchical Reinforcement Learning for Quadruped Locomotion
• Towards General and Autonomous Learning of Core Skills: A Case Study in Locomotion
• Learning Generalizable Locomotion Skills with Hierarchical Reinforcement Learning
• Template Model Inspired Task Space Learning for Robust Bipedal Locomotion
• Hierarchical Reinforcement Learning By Discovering Intrinsic Options