English
Related papers

Related papers: MuDreamer: Learning Predictive World Models withou…

200 papers

The deployment of Reinforcement Learning (RL) in real-world applications is constrained by its failure to satisfy safety criteria. Existing Safe Reinforcement Learning (SafeRL) methods, which rely on cost functions to enforce safety, often…

Machine Learning · Computer Science 2024-08-09 Weidong Huang , Jiaming Ji , Chunhe Xia , Borong Zhang , Yaodong Yang

We train embodied neural networks to plan and navigate unseen complex 3D environments, emphasising real-world deployment. Rather than requiring prior knowledge of the agent or environment, the planner learns to model the state transitions…

Robotics · Computer Science 2022-06-03 Shu Ishida , João F. Henriques

World models power some of the most efficient reinforcement learning algorithms. In this work, we showcase that they can be harnessed for continual learning - a situation when the agent faces changing environments. World models typically…

Simulation-to-reality reinforcement learning (RL) faces the critical challenge of reconciling discrepancies between simulated and real-world dynamics, which can severely degrade agent performance. A promising approach involves learning…

Machine Learning · Computer Science 2025-04-04 JB Lanier , Kyungmin Kim , Armin Karamzade , Yifei Liu , Ankita Sinha , Kat He , Davide Corsi , Roy Fox

In this work, we present Curled-Dreamer, a novel reinforcement learning algorithm that integrates contrastive learning into the DreamerV3 framework to enhance performance in visual reinforcement learning tasks. By incorporating the…

Machine Learning · Computer Science 2024-09-04 Victor Augusto Kich , Jair Augusto Bottega , Raul Steinmetz , Ricardo Bedin Grando , Ayano Yorozu , Akihisa Ohya

Training an agent to solve control tasks directly from high-dimensional images with model-free reinforcement learning (RL) has proven difficult. A promising approach is to learn a latent representation together with the control policy.…

Machine Learning · Computer Science 2020-07-10 Denis Yarats , Amy Zhang , Ilya Kostrikov , Brandon Amos , Joelle Pineau , Rob Fergus

Humans have an innate ability to decompose their perceptions of the world into objects and their attributes, such as colors, shapes, and movement patterns. This cognitive process enables us to imagine novel futures by recombining familiar…

Computer Vision and Pattern Recognition · Computer Science 2025-04-11 Junyeob Baek , Yi-Fu Wu , Gautam Singh , Sungjin Ahn

Delays frequently occur in real-world environments, yet standard reinforcement learning (RL) algorithms often assume instantaneous perception of the environment. We study random sensor delays in POMDPs, where observations may arrive…

Machine Learning · Computer Science 2026-04-17 Armin Karamzade , Kyungmin Kim , JB Lanier , Davide Corsi , Roy Fox

To safely navigate intricate real-world scenarios, autonomous vehicles must be able to adapt to diverse road conditions and anticipate future events. World model (WM) based reinforcement learning (RL) has emerged as a promising approach by…

Robotics · Computer Science 2024-07-29 Dechen Gao , Shuangyu Cai , Hanchu Zhou , Hang Wang , Iman Soltani , Junshan Zhang

World models learn general knowledge from videos and simulate experience for training behaviors in imagination, offering a path towards intelligent agents. However, previous world models have been unable to accurately predict object…

Artificial Intelligence · Computer Science 2025-09-30 Danijar Hafner , Wilson Yan , Timothy Lillicrap

Deep Reinforcement learning (DRL) is used to enable autonomous navigation in unknown environments. Most research assume perfect sensor data, but real-world environments may contain natural and artificial sensor noise and denial. Here, we…

Robotics · Computer Science 2024-10-21 Mariusz Wisniewski , Paraskevas Chatzithanos , Weisi Guo , Antonios Tsourdos

Mask-based lensless imagers are smaller and lighter than traditional lensed cameras. In these imagers, the sensor does not directly record an image of the scene; rather, a computational algorithm reconstructs it. Typically, mask-based…

Image and Video Processing · Electrical Eng. & Systems 2019-09-27 Kristina Monakhova , Joshua Yurtsever , Grace Kuo , Nick Antipa , Kyrollos Yanny , Laura Waller

Current control algorithms for aerial robots struggle with robustness in dynamic environments and adverse conditions. Model-based reinforcement learning (RL) has shown strong potential in handling these challenges while remaining…

Robotics · Computer Science 2025-11-25 Eashan Vytla , Bhavanishankar Kalavakolanu , Andrew Perrault , Matthew McCrink

The utility of learning a dynamics/world model of the environment in reinforcement learning has been shown in a many ways. When using neural networks, however, these models suffer catastrophic forgetting when learned in a lifelong or…

Machine Learning · Computer Science 2019-06-12 Nicholas Ketz , Soheil Kolouri , Praveen Pilly

Differentiable renderers have been used successfully for unsupervised 3D structure learning from 2D images because they can bridge the gap between 3D and 2D. To optimize 3D shape parameters, current renderers rely on pixel-wise losses…

Computer Vision and Pattern Recognition · Computer Science 2020-07-14 Zhizhong Han , Chao Chen , Yu-Shen Liu , Matthias Zwicker

Occupancy prediction reconstructs 3D structures of surrounding environments. It provides detailed information for autonomous driving planning and navigation. However, most existing methods heavily rely on the LiDAR point clouds to generate…

Computer Vision and Pattern Recognition · Computer Science 2024-08-22 Chubin Zhang , Juncheng Yan , Yi Wei , Jiaxin Li , Li Liu , Yansong Tang , Yueqi Duan , Jiwen Lu

Humans leverage rich internal models of the world to reason about the future, imagine counterfactuals, and adapt flexibly to new situations. In Reinforcement Learning (RL), world models aim to capture how the environment evolves in response…

Artificial Intelligence · Computer Science 2025-10-29 Léopold Maytié , Roland Bertin Johannet , Rufin VanRullen

Agents navigating in 3D environments require some form of memory, which should hold a compact and actionable representation of the history of observations useful for decision taking and planning. In most end-to-end learning approaches the…

Robotics · Computer Science 2023-10-02 Guillaume Bono , Leonid Antsfeld , Assem Sadek , Gianluca Monaci , Christian Wolf

Recent advancements in deep learning opened new opportunities for learning a high-quality 3D model from a single 2D image given sufficient training on large-scale data sets. However, the significant imbalance between available amount of…

Computer Vision and Pattern Recognition · Computer Science 2017-11-28 Lingjing Wang , Yi Fang

Building a robust perception module is crucial for visuomotor policy learning. While recent methods incorporate pre-trained 2D foundation models into robotic perception modules to leverage their strong semantic understanding, they struggle…

Robotics · Computer Science 2025-07-14 Wenbo Cui , Chengyang Zhao , Yuhui Chen , Haoran Li , Zhizheng Zhang , Dongbin Zhao , He Wang