DreamingV2: Reinforcement Learning with Discrete World Models without Reconstruction

• URL: http://arxiv.org/abs/2203.00494v1
• Date: Tue, 1 Mar 2022 14:44:15 GMT
• Title: DreamingV2: Reinforcement Learning with Discrete World Models without Reconstruction
• Abstract summary: The present paper proposes a novel reinforcement learning method with world models, DreamingV2. DreamingV2 is a collaborative extension of DreamerV2 and Dreaming. We believe DreamingV2 will be a reliable solution for robot learning since its discrete representation is suitable to describe discontinuous environments.
• Score: 14.950054143767824
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The present paper proposes a novel reinforcement learning method with world models, DreamingV2, a collaborative extension of DreamerV2 and Dreaming. DreamerV2 is a cutting-edge model-based reinforcement learning from pixels that uses discrete world models to represent latent states with categorical variables. Dreaming is also a form of reinforcement learning from pixels that attempts to avoid the autoencoding process in general world model training by involving a reconstruction-free contrastive learning objective. The proposed DreamingV2 is a novel approach of adopting both the discrete representation of DreamingV2 and the reconstruction-free objective of Dreaming. Compared to DreamerV2 and other recent model-based methods without reconstruction, DreamingV2 achieves the best scores on five simulated challenging 3D robot arm tasks. We believe that DreamingV2 will be a reliable solution for robot learning since its discrete representation is suitable to describe discontinuous environments, and the reconstruction-free fashion well manages complex vision observations.

Related papers

• Dreaming in Flow: Generative Grounding Feedback for Self-Evolving Unified Multimodal Models [55.231245660246934]
  Unified multimodal models integrate visual understanding and generation within a single network, yet the two capabilities are commonly optimized as separate tasks.<n>We introduce Generative Grounding Feedback, a self-evolving post-training framework that uses only text prompts and the model's own visual experience.
  arXiv  Detail & Related papers  (2026-09-08T05:52:53Z)
• Native Video-Action Pretraining for Generalizable Robot Control [77.59831077077176]
  LingBot-VA 2.0 is a video-action foundation model built from the ground up for embodiment.<n>To meet the demands of high-frequency inference, our model employs a sparse MoE backbone.<n>Real-world deployment validates LingBot-VA 2.0 as a robust foundation model.
  arXiv  Detail & Related papers  (2026-07-09T16:15:43Z)
• Self-supervised Hierarchical Visual Reasoning with World Model [82.64295546475257]
  3D open-world environments with adversarial opponents remain a core challenge for reinforcement learning.<n>We propose ResDreamer, a hierarchical world model in which each higher-level layer is trained to reconstruct the residuals of the layer below.<n>This design enables progressive abstraction of increasingly sophisticated world dynamics and fosters the emergence of richer latent representations.
  arXiv  Detail & Related papers  (2026-05-17T16:42:42Z)
• Dream2Learn: Structured Generative Dreaming for Continual Learning [15.555279110364706]
  We introduce Dream2Learn, a framework in which a model autonomously generates structured synthetic experiences from its own internal representations.<n>By integrating dreamed classes into continual training, D2L proactively structures latent features to support forward knowledge transfer and adaptation to future tasks.
  arXiv  Detail & Related papers  (2026-03-02T14:52:10Z)
• World Action Models are Zero-shot Policies [111.91938055103633]
  We introduce DreamZero, a World Action Model (WAM) built upon a pretrained video diffusion backbone.<n>By jointly modeling video and action, DreamZero learns diverse skills effectively from heterogeneous robot data.<n>We demonstrate two forms of cross-embodiment transfer: video-only demonstrations from other robots or humans yield a relative improvement of over 42% on unseen task performance.
  arXiv  Detail & Related papers  (2026-02-17T15:04:02Z)
• TransDreamerV3: Implanting Transformer In DreamerV3 [0.0]
  This paper introduces TransDreamerV3, a reinforcement learning model that enhances the DreamerV3 architecture by integrating a transformer encoder.<n>We conducted experiments on Atari-Boxing, Atari-Freeway, Atari-Pong, and Crafter tasks, where TransDreamerV3 demonstrated improved performance over DreamerV3.
  arXiv  Detail & Related papers  (2025-06-20T16:09:17Z)
• DreamGen: Unlocking Generalization in Robot Learning through Video World Models [120.25799361925387]
  DreamGen is a pipeline for training robot policies that generalize across behaviors and environments through neural trajectories.<n>Our work establishes a promising new axis for scaling robot learning well beyond manual data collection.
  arXiv  Detail & Related papers  (2025-05-19T04:55:39Z)
• Seedream 3.0 Technical Report [62.85849652170507]
  Seedream 3.0 is a high-performance Chinese-English bilingual image generation foundation model. We develop several technical improvements to address existing challenges in Seedream 2.0. Seedream 3.0 provides native high-resolution output (up to 2K) allowing it to generate images with high visual quality.
  arXiv  Detail & Related papers  (2025-04-15T16:19:07Z)
• VistaDream: Sampling multiview consistent images for single-view scene reconstruction [63.991582576387856]
  VistaDream is a framework to reconstruct a 3D scene from a single-view image. Recent diffusion models enable generating high-quality novel-view images from a single-view input image.
  arXiv  Detail & Related papers  (2024-10-22T10:55:59Z)
• Dreaming is All You Need [6.706761900460658]
  This research introduces two novel deep learning models, SleepNet and DreamNet, to strike a balance between exploration and precision. SleepNet seamlessly integrates supervised learning with unsupervised sleep" stages using pre-trained encoder models. DreamNet employs full encoder-decoder frameworks to reconstruct the hidden states, mimicking the human "dreaming" process.
  arXiv  Detail & Related papers  (2024-09-03T06:04:39Z)
• MuDreamer: Learning Predictive World Models without Reconstruction [58.0159270859475]
  We present MuDreamer, a robust reinforcement learning agent that builds upon the DreamerV3 algorithm by learning a predictive world model without the need for reconstructing input signals. Our method achieves comparable performance on the Atari100k benchmark while benefiting from faster training.
  arXiv  Detail & Related papers  (2024-05-23T22:09:01Z)
• DreamCreature: Crafting Photorealistic Virtual Creatures from Imagination [140.1641573781066]
  We introduce a novel task, Virtual Creatures Generation: Given a set of unlabeled images of the target concepts, we aim to train a T2I model capable of creating new, hybrid concepts. We propose a new method called DreamCreature, which identifies and extracts the underlying sub-concepts. The T2I thus adapts to generate novel concepts with faithful structures and photorealistic appearance.
  arXiv  Detail & Related papers  (2023-11-27T01:24:31Z)
• DriveDreamer: Towards Real-world-driven World Models for Autonomous Driving [76.24483706445298]
  We introduce DriveDreamer, a world model entirely derived from real-world driving scenarios. In the initial phase, DriveDreamer acquires a deep understanding of structured traffic constraints, while the subsequent stage equips it with the ability to anticipate future states. DriveDreamer enables the generation of realistic and reasonable driving policies, opening avenues for interaction and practical applications.
  arXiv  Detail & Related papers  (2023-09-18T13:58:42Z)
• Dropout's Dream Land: Generalization from Learned Simulators to Reality [33.9093915440877]
  A World Model is a generative model used to simulate an environment. In this work we explore improving the generalization capabilities from dream environments to real environments. We present a general approach to improve a controller's ability to transfer from a neural network dream environment to reality.
  arXiv  Detail & Related papers  (2021-09-17T03:58:56Z)
• Mastering Atari with Discrete World Models [61.7688353335468]
  We introduce DreamerV2, a reinforcement learning agent that learns behaviors purely from predictions in the compact latent space of a powerful world model. DreamerV2 constitutes the first agent that achieves human-level performance on the Atari benchmark of 55 tasks by learning behaviors inside a separately trained world model.
  arXiv  Detail & Related papers  (2020-10-05T17:52:14Z)
• Dreaming: Model-based Reinforcement Learning by Latent Imagination without Reconstruction [14.950054143767824]
  We propose a decoder-free extension of Dreamer, a leading model-based reinforcement learning (MBRL) method from pixels. We derive a likelihood-free and InfoMax objective of contrastive learning from the evidence lower bound of Dreamer. In comparison to Dreamer and other recent model-free reinforcement learning methods, our newly devised Dreamer with InfoMax and without generative decoder (Dreaming) achieves the best scores on 5 difficult simulated robotics tasks.
  arXiv  Detail & Related papers  (2020-07-29T00:14:40Z)
• Large-Scale Adversarial Training for Vision-and-Language Representation Learning [81.76089876263175]
  We present VILLA, the first known effort on large-scale adversarial training for vision-and-language (V+L) representation learning. VILLA consists of two training stages: (i) task-agnostic adversarial pre-training; followed by (ii) task-specific adversarial finetuning.
  arXiv  Detail & Related papers  (2020-06-11T05:14:35Z)

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.