iQRL -- Implicitly Quantized Representations for Sample-efficient Reinforcement Learning

• URL: http://arxiv.org/abs/2406.02696v1
• Date: Tue, 4 Jun 2024 18:15:44 GMT
• Title: iQRL -- Implicitly Quantized Representations for Sample-efficient Reinforcement Learning
• Authors: Aidan Scannell, Kalle Kujanpää, Yi Zhao, Mohammadreza Nakhaei, Arno Solin, Joni Pajarinen,
• Abstract summary: We propose an efficient representation learning method using only a self-supervised latent-state consistency loss. We achieve high performance and prevent representation collapse by quantizing the latent representation. Our method, named iQRL: implicitly Quantized Reinforcement Learning, is straightforward, compatible with any model-free RL algorithm.
• Score: 24.684363928059113
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Learning representations for reinforcement learning (RL) has shown much promise for continuous control. We propose an efficient representation learning method using only a self-supervised latent-state consistency loss. Our approach employs an encoder and a dynamics model to map observations to latent states and predict future latent states, respectively. We achieve high performance and prevent representation collapse by quantizing the latent representation such that the rank of the representation is empirically preserved. Our method, named iQRL: implicitly Quantized Reinforcement Learning, is straightforward, compatible with any model-free RL algorithm, and demonstrates excellent performance by outperforming other recently proposed representation learning methods in continuous control benchmarks from DeepMind Control Suite.

Related papers

Err

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.