Deakin University
Browse

File(s) under permanent embargo

A Robust Approach for Continuous Interactive Reinforcement Learning

conference contribution
posted on 2020-01-01, 00:00 authored by C Millán-Arias, B Fernandes, Francisco Cruz Naranjo, Richard DazeleyRichard Dazeley, Siona Fernandes
Interactive reinforcement learning is an approach in which an external trainer helps an agent to learn through advice. A trainer is useful in large or continuous scenarios; however, when the characteristics of the environment change over time, it can affect the learning. Robust reinforcement learning is a reliable approach that allows an agent to learn a task, regardless of disturbances in the environment. In this work, we present an approach that addresses interactive reinforcement learning problems in a dynamic environment with continuous states and actions. Our results show that the proposed approach allows an agent to complete the cart-pole balancing task satisfactorily in a dynamic, continuous action-state domain.

History

Event

Human-Agent Interaction. International conference (8th : 2020 : Virtual Event U.S.A.)

Pagination

278 - 280

Publisher

ACM

Location

Virtual Event

Start date

2020-11-10

End date

2020-11-13

ISBN-13

9781450380546

Language

eng

Publication classification

E2 Full written paper - non-refereed / Abstract reviewed

Title of proceedings

HAI 2020 - Proceedings of the 8th International Conference on Human-Agent Interaction

Usage metrics

    Research Publications

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC