Learning to Explore by Reinforcement over High-Level Options

11/02/2021
by   Liu Juncheng, et al.
0

Autonomous 3D environment exploration is a fundamental task for various applications such as navigation. The goal of exploration is to investigate a new environment and build its occupancy map efficiently. In this paper, we propose a new method which grants an agent two intertwined options of behaviors: "look-around" and "frontier navigation". This is implemented by an option-critic architecture and trained by reinforcement learning algorithms. In each timestep, an agent produces an option and a corresponding action according to the policy. We also take advantage of macro-actions by incorporating classic path-planning techniques to increase training efficiency. We demonstrate the effectiveness of the proposed method on two publicly available 3D environment datasets and the results show our method achieves higher coverage than competing techniques with better efficiency.

READ FULL TEXT

page 2

page 8

research
01/07/2022

Attention Option-Critic

Temporal abstraction in reinforcement learning is the ability of an agen...
research
05/13/2019

Learning and Exploiting Multiple Subgoals for Fast Exploration in Hierarchical Reinforcement Learning

Hierarchical Reinforcement Learning (HRL) exploits temporally extended a...
research
01/30/2021

Stay Alive with Many Options: A Reinforcement Learning Approach for Autonomous Navigation

Hierarchical reinforcement learning approaches learn policies based on h...
research
12/06/2022

Variable-Decision Frequency Option Critic

In classic reinforcement learning algorithms, agents make decisions at d...
research
06/03/2022

Option Discovery for Autonomous Generation of Symbolic Knowledge

In this work we present an empirical study where we demonstrate the poss...
research
03/03/2020

Efficient Exploration in Constrained Environments with Goal-Oriented Reference Path

In this paper, we consider the problem of building learning agents that ...
research
09/05/2021

Hierarchical Object-to-Zone Graph for Object Navigation

The goal of object navigation is to reach the expected objects according...

Please sign up or login with your details

Forgot password? Click here to reset