Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Authors: Hlynur Davíð Hlynsson and Laurenz Wiskott

Affiliation: Institut für Neuroinformatik, Ruhr-Universität Bochum, Universitätsstraße 150, Bochum, Germany

Keyword(s): Reinforcement Learning, Representation Learning, Deep Learning, Machine Learning.

Abstract: One of the fundamental challenges in reinforcement learning (RL) is the one of data efficiency: modern algorithms require a very large number of training samples, especially compared to humans, for solving environments with high-dimensional observations. The severity of this problem is increased when the reward signal is sparse. In this work, we propose learning a state representation in a self-supervised manner for reward prediction. The reward predictor learns to estimate either a raw or a smoothed version of the true reward signal in an environment with a single terminating goal state. We augment the training of out-of-the-box RL agents in single-goal environments with visual inputs by shaping the reward using our reward predictor during policy learning. Using our representation for preprocessing high-dimensional observations, as well as using the predictor for reward shaping, is shown to facilitate faster learning of Actor Critic using Kronecker-factored Trust Region and Proximal Policy Optimization. (More)

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 13.58.74.190

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Hlynsson, H. D. and Wiskott, L. (2021). Reward Prediction for Representation Learning and Reward Shaping. In Proceedings of the 13th International Joint Conference on Computational Intelligence (IJCCI 2021) - NCTA; ISBN 978-989-758-534-0; ISSN 2184-3236, SciTePress, pages 267-276. DOI: 10.5220/0010640200003063

@conference{ncta21,
author={Hlynur Davíð Hlynsson and Laurenz Wiskott},
title={Reward Prediction for Representation Learning and Reward Shaping},
booktitle={Proceedings of the 13th International Joint Conference on Computational Intelligence (IJCCI 2021) - NCTA},
year={2021},
pages={267-276},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010640200003063},
isbn={978-989-758-534-0},
issn={2184-3236},
}

TY - CONF

JO - Proceedings of the 13th International Joint Conference on Computational Intelligence (IJCCI 2021) - NCTA
TI - Reward Prediction for Representation Learning and Reward Shaping
SN - 978-989-758-534-0
IS - 2184-3236
AU - Hlynsson, H.
AU - Wiskott, L.
PY - 2021
SP - 267
EP - 276
DO - 10.5220/0010640200003063
PB - SciTePress