Skip to main content
Home
ENHU

Main navigation

  • Discover
    • News
    • Events
  • Research & development
    • Areas of application
    • Research topics
  • Resources
    • Publications
    • Lead researchers
  • Partners
    • Consortium members
    • International partners
    • Industry contacts
    • University contacts
  1. Home
  2. Publications
Transportation Research Procedia, Volume 62 / 11 March 2022

Investigating Successor Features in the Domain of Autonomous Vehicle Control

Széchenyi Plusz RRF

In this article, the basic Reinforcement Learning (RL) concepts are discussed, continued with a brief explanation of Markov Decision Processes (MDPs). Reasoning for the application of RL in the autonomous vehicle control domain is accompanied with a developed basic environment for simulation-based training of agents. Furthermore, we look at the available literature of successor features, and the recent achievements of its utilization. Our motivation is to tackle the problem of credit assignment with reward decomposition by using successor features, because the complex tasks while driving can cause unsuccessful training and can be challenging. After explaining the applied methodology and showing how it works, state-of-the-art ideas are investigated and infused into the vehicle control realm. Moreover, the paper details how these features can be tailored to the highway driving scenarios and what is the secret behind its capability to boost the performance of the RL agent. In order to investigate the proposed problems in a credible way we applied a high-fidelity traffic simulator (SUMO) as our environment, and concluded different trainings based on various scenarios. We present successor features applied to an autonomous vehicle control setting, such as highway commute. Our results imply that learned skills can help with the multi-objective rewarding problem, and agents applied to changing reward systems can adapt quickly to the new tasks. The only thing to find is the correct decomposition and selection of successor features.

Url
https://doi.org/10.1016/j.trpro.2022.02.023
Authors
Szőke, L.
Aradi, Sz.
Tettamanti, T.
Institutes

Kapcsolat

Prof. Dr. Péter Gáspár

Hungary, H-1111 Budapest,
Kende u. 13-17.
+36 1 279 6000
autonom@nemzetilabor.hu

© 2020-2023 National Laboratory for Autonomous Systems, Budapest