iQRL -- Implicitly Quantized Representations for Sample-efficient Reinforcement Learning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911904895598592 |
|---|---|
| author | Scannell, Aidan Kujanpää, Kalle Zhao, Yi Nakhaei, Mohammadreza Solin, Arno Pajarinen, Joni |
| author_facet | Scannell, Aidan Kujanpää, Kalle Zhao, Yi Nakhaei, Mohammadreza Solin, Arno Pajarinen, Joni |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_02696 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | iQRL -- Implicitly Quantized Representations for Sample-efficient Reinforcement Learning Scannell, Aidan Kujanpää, Kalle Zhao, Yi Nakhaei, Mohammadreza Solin, Arno Pajarinen, Joni Machine Learning 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. |
| title | iQRL -- Implicitly Quantized Representations for Sample-efficient Reinforcement Learning |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2406.02696 |