Next Embedding Prediction Makes World Models Stronger
Capturing temporal dependencies is critical for model-based reinforcement learning (MBRL) in partially observable, high-dimensional domains. We introduce NE-Dreamer, a decoder-free MBRL agent that leverages a temporal transformer to predict next-step encoder embeddings from latent state sequences, directly optimizing temporal predictive alignment in representation space. This approach enables NE-Dreamer to learn coherent, predictive state representations without reconstruction losses or auxiliary supervision. On the DeepMind Control Suite, NE-Dreamer matches or exceeds the performance of DreamerV3 and leading decoder-free agents. On a challenging subset of DMLab tasks involving memory and spatial reasoning, NE-Dreamer achieves substantial gains. These results establish next-embedding prediction with temporal transformers as an effective, scalable framework for MBRL in complex, partially observable environments.
Code (0)
등록된 구현이 없습니다.
Tasks
Reinforcement LearningSpatial ReasoningSimilar Papers 제목 키워드 기반
Orca: The World is in Your Mind
We introduce Orca, an initial instantiation of a general world foundation model. Orca learns a unified world latent space from multimodal world signals and exposes it through multimodal readout interfaces. Rather than op…
Text GenerationListening Forward: Next Patch Embedding Prediction Enables Scalable Audio Learners
Self-supervised learning (SSL) has driven substantial progress in audio representation learning, though existing methods have increasingly relied on elaborate pre-training recipes to reach competitive performance. A mark…
Self-Supervised LearningRepresentation LearningNext-Embedding Prediction Makes Strong Vision Learners
Inspired by the success of generative pretraining in natural language, we ask whether the same principles can yield strong self-supervised visual learners. Instead of training models to output features for downstream use…
Self-Supervised LearningSemantic SegmentationTransTARec: Time-Adaptive Translating Embedding Model for Next POI Recommendation
The rapid growth of location acquisition technologies makes Point-of-Interest(POI) recommendation possible due to redundant user check-in records. In this paper, we focus on next POI recommendation in which next POI is b…
TripletCross-Network Social User Embedding with Hybrid Differential Privacy Guarantees
Integrating multiple online social networks (OSNs) has important implications for many downstream social mining tasks, such as user preference modelling, recommendation, and link prediction. However, it is unfortunately …
AttributeLink PredictionNetwork EmbeddingPrivacy Preserving