Masked Autoencoding For Scalable And Generalizable Decision Making

Abstract

We are interested in learning scalable agents for reinforcement learning that can learn from large-scale, diverse sequential data similar to current large vision and language models. To this end, this paper presents masked decision prediction (MaskDP), a simple and scalable self-supervised pretraining method for reinforcement learning (RL) and behavioral cloning (BC). In our MaskDP approach, we employ a masked autoencoder (MAE) to state-action trajectories, wherein we randomly mask state and action tokens and reconstruct the missing data. By doing so, the model is required to infer masked-out states and actions and extract information about dynamics. We find that masking different proportions of the input sequence significantly helps with learning a better model that generalizes well to multiple downstream tasks. In our empirical study, we find that a MaskDP model gains the capability of zero-shot transfer to new BC tasks, such as single and multiple goal reaching, and it can zero-shot

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyliu2022masked

Related papers

• MA2RL: Masked Autoencoders For Generalizable Multi-agent Reinforcement Learning (2025)0.00
• Reprem: Representation Pre-training With Masked Model For Reinforcement Learning (2023)0.00
• MAGIC-MASK: Multi-agent Guided Inter-agent Collaboration With Mask-based Explainability For Reinforcement Learning (2025)0.00
• M\(^3\)PC: Test-time Model Predictive Control For Pretrained Masked Trajectory Model (2024)0.00
• MDPO: Overcoming The Training-inference Divide Of Masked Diffusion Language Models (2025)0.00
• Mask Atari For Deep Reinforcement Learning As POMDP Benchmarks (2022)0.00
• Towards Principled Representation Learning From Videos For Reinforcement Learning (2024)0.00
• CAMEL: Continuous Action Masking Enabled By Large Language Models For Reinforcement Learning (2025)0.00