Mask-based Predictive Representations for Reinforcement Learning

2026-07-05 · Kai Zhao arxiv

Vision-based deep reinforcement learning involves dealing with high-dimensional inputs of image information. It is crucial to abstract effective states from high-dimensional image inputs and limited samples for sample-efficient reinforcement learning. To address this challenge, inspired by fields such as natural language processing and computer vision, we propose a self-supervised task based on mask prediction as an auxiliary task for reinforcement learning. This non-reconstruction method uses the sequence information collected by the agent from the environment and the context information in the sequence to predict the masked information, thereby strengthening the agent's understanding of the task and learning effective representations. Combined with transformers, we find that the model reconstructs the masked input sequence in the latent space. By feeding the compressed representations learned by this method into reinforcement learning models, we observe an improvement in the sample efficiency of reinforcement learning. Moreover, the model outperforms state-of-the-art sample-efficient reinforcement learning methods on multiple continuous and discrete control benchmarks.

📄 PDF Abstract BibTeX arXiv:2607.04153

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

RePAIR: Predictive Self-Supervised Representation Learning in Chess

2026-06-10 · Christoph Koller, Johannes Fürnkranz, Timo Bertram arxiv

In this paper, we introduce Representation Prediction via Autoencoding using Iterative Refinement (RePAIR) - a novel self-supervised representation learning architecture that synthesizes Masked Autoencoders (MAE), Joint …

Representation Learning Reinforcement Learning

Learning predictive representations in autonomous driving to improve deep reinforcement learning

2020-06-26 · Daniel Graves, Nhat M. Nguyen, Kimia Hassanzadeh, Jun Jin

Reinforcement learning using a novel predictive representation is applied to autonomous driving to accomplish the task of driving between lane markings where substantial benefits in performance and generalization are obs…

Autonomous Driving Deep Reinforcement Learning reinforcement-learning Reinforcement Learning+1

Environment Predictive Coding for Embodied Agents

2021-02-03 · Santhosh K. Ramakrishnan, Tushar Nagarajan, Ziad Al-Halah, Kristen Grauman

We introduce environment predictive coding, a self-supervised approach to learn environment-level representations for embodied agents. In contrast to prior work on self-supervised learning for images, we aim to jointly e…

Self-Supervised Learning

Mask-based Latent Reconstruction for Reinforcement Learning

2022-01-28 · Tao Yu, Zhizheng Zhang, Cuiling Lan, Yan Lu 외

For deep reinforcement learning (RL) from pixels, learning effective state representations is crucial for achieving high performance. However, in practice, limited experience and high-dimensional inputs prevent effective…

Deep Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)+1

M$^3$PC: Test-time Model Predictive Control for Pretrained Masked Trajectory Model

2024-12-07 · Kehan Wen, Yutong Hu, Yao Mu, Lei Ke

Recent work in Offline Reinforcement Learning (RL) has shown that a unified Transformer trained under a masked auto-encoding objective can effectively capture the relationships between different modalities (e.g., states,…

D4RL model Model Predictive Control Reinforcement Learning (RL)