English
Related papers

Related papers: World Model as a Graph: Learning Latent Landmarks …

200 papers

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

Reinforcement Learning (RL) methods are typically applied directly in environments to learn policies. In some complex environments with continuous state-action spaces, sparse rewards, and/or long temporal horizons, learning a good policy in…

Machine Learning · Computer Science 2023-05-03 Deyao Zhu , Li Erran Li , Mohamed Elhoseiny

Solving long-horizon, temporally-extended tasks using Reinforcement Learning (RL) is challenging, compounded by the common practice of learning without prior knowledge (or tabula rasa learning). Humans can generate and execute plans with…

Machine Learning · Computer Science 2023-11-10 Bharat Prakash , Tim Oates , Tinoosh Mohsenin

Reinforcement Learning (RL) is notoriously data-inefficient, which makes training on a real robot difficult. While model-based RL algorithms (world models) improve data-efficiency to some extent, they still require hours or days of…

Machine Learning · Computer Science 2023-10-25 Yunhai Feng , Nicklas Hansen , Ziyan Xiong , Chandramouli Rajagopalan , Xiaolong Wang

World models enable long-horizon planning by internally generating and evaluating imagined trajectories, making them a promising foundation for generalist agents. However, this imagination-driven decision process also introduces new…

Machine Learning · Computer Science 2026-05-05 Siyuan Duan , Ke Zhang , Xizhao Luo

Planning has been very successful for control tasks with known environment dynamics. To leverage planning in unknown environments, the agent needs to learn the dynamics from interactions with the world. However, learning dynamics models…

Machine Learning · Computer Science 2019-06-06 Danijar Hafner , Timothy Lillicrap , Ian Fischer , Ruben Villegas , David Ha , Honglak Lee , James Davidson

Long-horizon task planning is essential for the development of intelligent assistive and service robots. In this work, we investigate the applicability of a smaller class of large language models (LLMs), specifically GPT-2, in robotic task…

Robotics · Computer Science 2023-05-16 Georgia Chalvatzaki , Ali Younes , Daljeet Nandha , An Le , Leonardo F. R. Ribeiro , Iryna Gurevych

Path planning in dynamic environments is a fundamental challenge in intelligent transportation and robotics, where obstacles and conditions change over time, introducing uncertainty and requiring continuous adaptation. While existing…

Robotics · Computer Science 2025-11-20 Jonas De Maeyer , Hossein Yarahmadi , Moharram Challenger

The objective of lifelong reinforcement learning (RL) is to optimize agents which can continuously adapt and interact in changing environments. However, current RL approaches fail drastically when environments are non-stationary and…

Machine Learning · Computer Science 2021-06-17 Kevin Lu , Aditya Grover , Pieter Abbeel , Igor Mordatch

The field of reinforcement learning (RL) is facing increasingly challenging domains with combinatorial complexity. For an RL agent to address these challenges, it is essential that it can plan effectively. Prior work has typically utilized…

A world model is an internal model that simulates how the world evolves. Given past observations and actions, it predicts the future physical state of both the embodied agent and its environment. Accurate world models are essential for…

Machine Learning · Computer Science 2026-04-22 Zaishuo Xia , Yukuan Lu , Xinyi Li , Yifan Xu , Yubei Chen

We explore building generative neural network models of popular reinforcement learning environments. Our world model can be trained quickly in an unsupervised manner to learn a compressed spatial and temporal representation of the…

Machine Learning · Computer Science 2018-05-10 David Ha , Jürgen Schmidhuber

Autonomous navigation of terrestrial robots using Reinforcement Learning (RL) from LIDAR observations remains challenging due to the high dimensionality of sensor data and the sample inefficiency of model-free approaches. Conventional…

To quickly solve new tasks in complex environments, intelligent agents need to build up reusable knowledge. For example, a learned world model captures knowledge about the environment that applies to new tasks. Similarly, skills capture…

Machine Learning · Computer Science 2021-05-04 Kevin Xie , Homanga Bharadhwaj , Danijar Hafner , Animesh Garg , Florian Shkurti

The increasing demand for autonomous systems in complex and dynamic environments has driven significant research into intelligent path planning methodologies. For decades, graph-based search algorithms, linear programming techniques, and…

In recent years, deep Reinforcement Learning (RL) has been successful in various combinatorial search domains, such as two-player games and scientific discovery. However, directly applying deep RL in planning domains is still challenging.…

Artificial Intelligence · Computer Science 2022-09-21 Dieqiao Feng , Carla P. Gomes , Bart Selman

Meta-learning is a line of research that develops the ability to leverage past experiences to efficiently solve new learning problems. Meta-Reinforcement Learning (meta-RL) methods demonstrate a capability to learn behaviors that…

Machine Learning · Computer Science 2022-08-25 Brieuc Pinon , Jean-Charles Delvenne , Raphaël Jungers

By combining classical planning methods with large language models (LLMs), recent research such as LLM+P has enabled agents to plan for general tasks given in natural language. However, scaling these methods to general-purpose service…

Robotics · Computer Science 2025-08-05 Krish Agarwal , Yuqian Jiang , Jiaheng Hu , Bo Liu , Peter Stone

Solving robotic navigation tasks via reinforcement learning (RL) is challenging due to their sparse reward and long decision horizon nature. However, in many navigation tasks, high-level (HL) task representations, like a rough floor plan,…

Robotics · Computer Science 2021-11-08 Jan Wöhlke , Felix Schmitt , Herke van Hoof

Large Language Models (LLMs) based agents have demonstrated remarkable potential in autonomous task-solving across complex, open-ended environments. A promising approach for improving the reasoning capabilities of LLM agents is to better…

Computation and Language · Computer Science 2025-11-12 Siyu Xia , Zekun Xu , Jiajun Chai , Wentian Fan , Yan Song , Xiaohan Wang , Guojun Yin , Wei Lin , Haifeng Zhang , Jun Wang