iQRL -- Implicitly Quantized Representations for Sample-efficient Reinforcement Learning
This work addresses sample efficiency in reinforcement learning for continuous control tasks, offering an incremental improvement over existing representation learning methods.
The paper tackles the problem of sample-efficient reinforcement learning in continuous control by proposing iQRL, a method that uses implicit quantization to preserve latent representation rank and prevent collapse, achieving high performance and outperforming other recent representation learning methods on DeepMind Control Suite benchmarks.
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.