Dreamer-CDP: Improving Reconstruction-free World Models Via Continuous Deterministic Representation Prediction

• URL: http://arxiv.org/abs/2603.07083v1
• Date: Sat, 07 Mar 2026 07:41:28 GMT
• Title: Dreamer-CDP: Improving Reconstruction-free World Models Via Continuous Deterministic Representation Prediction
• Abstract summary: We introduce a JEPA-style predictor defined on continuous, deterministic representations.<n>Our method matches Dreamer's performance on Crafter, demonstrating effective world model learning on this benchmark without reconstruction objectives.
• Score: 8.228889210180268
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Model-based reinforcement learning (MBRL) agents operating in high-dimensional observation spaces, such as Dreamer, rely on learning abstract representations for effective planning and control. Existing approaches typically employ reconstruction-based objectives in the observation space, which can render representations sensitive to task-irrelevant details. Recent alternatives trade reconstruction for auxiliary action prediction heads or view augmentation strategies, but perform worse in the Crafter environment than reconstruction-based methods. We close this gap between Dreamer and reconstruction-free models by introducing a JEPA-style predictor defined on continuous, deterministic representations. Our method matches Dreamer's performance on Crafter, demonstrating effective world model learning on this benchmark without reconstruction objectives.

Related papers

• Large Vision-Language Models Get Lost in Attention [51.851592109135716]
  We propose a unified framework grounded in information theory and geometry to quantify the geometric and entropic nature of residual updates.<n>Applying this unified framework reveals a fundamental functional decoupling: Attention acts as a subspace-language operator focused on reconfiguration, whereas FFNs serve as subspace-language operators driving semantic innovation.
  arXiv  Detail & Related papers  (2026-05-07T04:45:52Z)
• Iterative Deployment Improves Planning Skills in LLMs [36.668436209940516]
  We show that iterative deployment of large language models (LLMs) can significantly change the properties of the resultant models.<n>By testing this mechanism on various planning domains, we observe substantial improvements in planning skills.<n>We then provide theoretical analysis showing that iterative deployment effectively implements reinforcement learning (RL) training in the outer-loop.
  arXiv  Detail & Related papers  (2025-12-31T16:03:14Z)
• Bounding Distributional Shifts in World Modeling through Novelty Detection [15.354352209595973]
  We use a variational autoencoder as a novelty detector to ensure that proposed action trajectories during planning do not cause the learned model to deviate from the training data distribution.<n>The proposed method improves over state-of-the-art solutions in terms of data efficiency.
  arXiv  Detail & Related papers  (2025-08-08T07:42:14Z)
• Model Steering: Learning with a Reference Model Improves Generalization Bounds and Scaling Laws [52.10468229008941]
  This paper formalizes an emerging learning paradigm that uses a trained model as a reference to guide and enhance the training of a target model through strategic data selection or weighting.<n>We provide theoretical insights into why this approach improves generalization and data efficiency compared to training without a reference model.<n>Building on these insights, we introduce a novel method for Contrastive Language-Image Pretraining with a reference model, termed DRRho-CLIP.
  arXiv  Detail & Related papers  (2025-05-10T16:55:03Z)
• Latent Diffusion Planning for Imitation Learning [78.56207566743154]
  Latent Diffusion Planning (LDP) is a modular approach consisting of a planner and inverse dynamics model.<n>By separating planning from action prediction, LDP can benefit from the denser supervision signals of suboptimal and action-free data.<n>On simulated visual robotic manipulation tasks, LDP outperforms state-of-the-art imitation learning approaches.
  arXiv  Detail & Related papers  (2025-04-23T17:53:34Z)
• Policy-shaped prediction: avoiding distractions in model-based reinforcement learning [2.0739760901716755]
  We develop a method for focusing the capacity of the world model through synergy of a pretrained segmentation model, a task-aware reconstruction loss, and adversarial learning.<n>Our method outperforms a variety of other approaches designed to reduce the impact of distractors, and is an advance towards robust model-based reinforcement learning.
  arXiv  Detail & Related papers  (2024-12-08T00:21:37Z)
• Jointly Training and Pruning CNNs via Learnable Agent Guidance and Alignment [69.33930972652594]
  We propose a novel structural pruning approach to jointly learn the weights and structurally prune architectures of CNN models. The core element of our method is a Reinforcement Learning (RL) agent whose actions determine the pruning ratios of the CNN model's layers. We conduct the joint training and pruning by iteratively training the model's weights and the agent's policy.
  arXiv  Detail & Related papers  (2024-03-28T15:22:29Z)
• ZhiJian: A Unifying and Rapidly Deployable Toolbox for Pre-trained Model Reuse [59.500060790983994]
  This paper introduces ZhiJian, a comprehensive and user-friendly toolbox for model reuse, utilizing the PyTorch backend. ZhiJian presents a novel paradigm that unifies diverse perspectives on model reuse, encompassing target architecture construction with PTM, tuning target model with PTM, and PTM-based inference.
  arXiv  Detail & Related papers  (2023-08-17T19:12:13Z)
• Simplifying Model-based RL: Learning Representations, Latent-space Models, and Policies with One Objective [142.36200080384145]
  We propose a single objective which jointly optimize a latent-space model and policy to achieve high returns while remaining self-consistent. We demonstrate that the resulting algorithm matches or improves the sample-efficiency of the best prior model-based and model-free RL methods.
  arXiv  Detail & Related papers  (2022-09-18T03:51:58Z)
• Goal-Directed Planning for Habituated Agents by Active Inference Using a Variational Recurrent Neural Network [5.000272778136268]
  This study shows that the predictive coding (PC) and active inference (AIF) frameworks can develop better generalization by learning a prior distribution in a low dimensional latent state space. In our proposed model, learning is carried out by inferring optimal latent variables as well as synaptic weights for maximizing the evidence lower bound. Our proposed model was evaluated with both simple and complex robotic tasks in simulation, which demonstrated sufficient generalization in learning with limited training data.
  arXiv  Detail & Related papers  (2020-05-27T06:43:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.