conftrace_

2021 IJCAI IJCAI 2021

Deep Reinforcement Learning with Hierarchical Structures

Abstract

Hierarchical reinforcement learning (HRL), which enables control at multiple time scales, is a promising paradigm to solve challenging and long-horizon tasks. In this paper, we briefly introduce our work in bottom-up and top-down HRL and outline the directions for future work.

Authors

Siyuan Li

Topics

Reinforcement Learning > Methods > Policy Learning Reinforcement Learning > Applications > Robotics

Keywords

hierarchical reinforcement learning temporal abstraction multi-time scale control

More from IJCAI 2021

All IJCAI 2021 papers →

Robot Manipulation Learning Using Generative Adversarial Imitation Learning

Planning and Reinforcement Learning for General-Purpose Service Robots

Nash Welfare in the Facility Location Problem

AI for Planning Public Health Interventions

Uncertain Time Series Classification

Combining Reinforcement Learning and Causal Models for Robotics Applications