---
res:
  bibo_abstract:
  - World models learn behaviors in a latent imagination space to enhance the sample-efficiency
    of deep reinforcement learning (RL) algorithms. While learning world models for
    high-dimensional observations (e.g., pixel inputs) has become practicable on standard
    RL benchmarks and some games, their effectiveness in real-world robotics applications
    has not been explored. In this paper, we investigate how such agents generalize
    to real-world autonomous vehicle control tasks, where advanced model-free deep
    RL algorithms fail. In particular, we set up a series of time-lap tasks for an
    F1TENTH racing robot, equipped with a high-dimensional LiDAR sensor, on a set
    of test tracks with a gradual increase in their complexity. In this continuous-control
    setting, we show that model-based agents capable of learning in imagination substantially
    outperform model-free agents with respect to performance, sample efficiency, successful
    task completion, and generalization. Moreover, we show that the generalization
    ability of model-based agents strongly depends on the choice of their observation
    model. We provide extensive empirical evidence for the effectiveness of world
    models provided with long enough memory horizons in sim2real tasks.@eng
  bibo_authorlist:
  - foaf_Person:
      foaf_givenName: Axel
      foaf_name: Brunnbauer, Axel
      foaf_surname: Brunnbauer
  - foaf_Person:
      foaf_givenName: Luigi
      foaf_name: Berducci, Luigi
      foaf_surname: Berducci
  - foaf_Person:
      foaf_givenName: Andreas
      foaf_name: Brandstatter, Andreas
      foaf_surname: Brandstatter
  - foaf_Person:
      foaf_givenName: Mathias
      foaf_name: Lechner, Mathias
      foaf_surname: Lechner
      foaf_workInfoHomepage: http://www.librecat.org/personId=3DC22916-F248-11E8-B48F-1D18A9856A87
  - foaf_Person:
      foaf_givenName: Ramin
      foaf_name: Hasani, Ramin
      foaf_surname: Hasani
  - foaf_Person:
      foaf_givenName: Daniela
      foaf_name: Rus, Daniela
      foaf_surname: Rus
  - foaf_Person:
      foaf_givenName: Radu
      foaf_name: Grosu, Radu
      foaf_surname: Grosu
  bibo_doi: 10.1109/ICRA46639.2022.9811650
  dct_date: 2022^xs_gYear
  dct_identifier:
  - UT:000941277600124
  dct_isPartOf:
  - http://id.crossref.org/issn/1050-4729
  - http://id.crossref.org/issn/9781728196817
  dct_language: eng
  dct_publisher: IEEE@
  dct_title: Latent imagination facilitates zero-shot transfer in autonomous racing@
...