Harnessing Discrete Representations For Continual Reinforcement Learning

Abstract

Reinforcement learning (RL) agents make decisions using nothing but observations from the environment, and consequently, heavily rely on the representations of those observations. Though some recent breakthroughs have used vector-based categorical representations of observations, often referred to as discrete representations, there is little work explicitly assessing the significance of such a choice. In this work, we provide a thorough empirical investigation of the advantages of representing observations as vectors of categorical values within the context of reinforcement learning. We perform evaluations on world-model learning, model-free RL, and ultimately continual RL problems, where the benefits best align with the needs of the problem setting. We find that, when compared to traditional continuous representations, world models learned over discrete representations accurately model more of the world with less capacity, and that agents trained with discrete representations learn be

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keymeyer2023harnessing

Related papers

• Value-consistent Representation Learning For Data-efficient Reinforcement Learning (2022)0.00
• Locally Constrained Representations In Reinforcement Learning (2022)0.00
• Learning To Play Atari In A World Of Tokens (2024)0.00
• A Survey Of Continual Reinforcement Learning (2025)0.00
• Unsupervised Representation Learning In Deep Reinforcement Learning: A Review (2022)9.59
• Bootstrapped Representations In Reinforcement Learning (2023)0.00
• Advancements And Challenges In Continual Reinforcement Learning: A Comprehensive Review (2025)0.00
• The Effectiveness Of World Models For Continual Reinforcement Learning (2022)0.00