English
Related papers

Related papers: Learning Local Constraints for Reinforcement-Learn…

200 papers

Recent procedural content generation via machine learning (PCGML) methods allow learning from existing content to produce similar content automatically. While these approaches are able to generate content for different games (e.g. Super…

Artificial Intelligence · Computer Science 2020-05-27 Vanessa Volz , Niels Justesen , Sam Snodgrass , Sahar Asadi , Sami Purmonen , Christoffer Holmgård , Julian Togelius , Sebastian Risi

The past decade has seen a rapid increase in the level of research interest in procedural content generation (PCG) for digital games, and there are now numerous research avenues focused on new approaches for driving and applying PCG…

Human-Computer Interaction · Computer Science 2022-10-06 Oliver Withington , Laurissa Tokarchuk

Constrained generative modeling is fundamental to applications such as robotic control and autonomous driving, where models must respect physical laws and safety-critical constraints. In real-world settings, these constraints rarely take…

Machine Learning · Computer Science 2026-03-10 Xiaoxuan Liang , Saeid Naderiparizi , Yunpeng Liu , Berend Zwartsenberg , Frank Wood

An AI system for professional floor plan design must precisely control room dimensions and areas while respecting the desired connectivity between rooms and maintaining functional and aesthetic quality. Existing generative approaches focus…

Computation and Language · Computer Science 2026-05-15 Luis Lara , Aristides Milios , Zhi Hao Luo , Aditya Sharma , Ge Ya Luo , Christopher Beckham , Florian Golemo , Christopher Pal

Procedural Content Generation (PCG) refers to the practice, in videogames and other games, of generating content such as levels, quests, or characters algorithmically. Motivated by the need to make games replayable, as well as to reduce…

Artificial Intelligence · Computer Science 2020-03-18 Sebastian Risi , Julian Togelius

The success of Reinforcement Learning (RL) heavily relies on the ability to learn robust representations from the observations of the environment. In most cases, the representations learned purely by the reinforcement learning loss can…

Machine Learning · Computer Science 2024-02-12 Somjit Nath , Rushiv Arora , Samira Ebrahimi Kahou

Graph data structures offer a versatile and powerful means to model relationships and interconnections in various domains, promising substantial advantages in data representation, analysis, and visualization. In games, graph-based data…

Machine Learning · Computer Science 2024-09-10 Florian Rupp , Kai Eckert

Goal-conditioned and Multi-Task Reinforcement Learning (GCRL and MTRL) address numerous problems related to robot learning, including locomotion, navigation, and manipulation scenarios. Recent works focusing on language-defined robotic…

Computation and Language · Computer Science 2023-06-21 Julien Perez , Denys Proux , Claude Roux , Michael Niemaz

Data-driven generative models excel in language and vision, but diffusion models often fail in constrained planning and design tasks, exhibiting severe constraint violations in engineering inverse design, molecular generation, multi-robot…

Computer Vision and Pattern Recognition · Computer Science 2026-05-14 Zirui Zhao , Boye Niu , Harold Soh , David Hsu , Wee Sun Lee

In this paper, we revisit endless online level generation with the recently proposed experience-driven procedural content generation via reinforcement learning (EDRL) framework. Inspired by an observation that EDRL tends to generate…

Artificial Intelligence · Computer Science 2023-03-27 Ziqi Wang , Tianye Shu , Jialin Liu

Deep generative neural networks have proven effective at both conditional and unconditional modeling of complex data distributions. Conditional generation enables interactive control, but creating new controls often requires expensive…

Machine Learning · Computer Science 2017-12-25 Jesse Engel , Matthew Hoffman , Adam Roberts

Expressive range analysis is a visualization-based technique used to evaluate the performance of generative models, particularly in game level generation. It typically employs two quantifiable metrics to position generated artifacts on a 2D…

Machine Learning · Computer Science 2025-04-09 Mahsa Bazzaz , Seth Cooper

Despite recent advances, goal-directed generation of structured discrete data remains challenging. For problems such as program synthesis (generating source code) and materials design (generating molecules), finding examples which satisfy…

Machine Learning · Computer Science 2020-10-26 Amina Mollaysa , Brooks Paige , Alexandros Kalousis

Wave Function Collapse (WFC) is a widely used tile-based algorithm in procedural content generation, including textures, objects, and scenes. However, the current WFC algorithm and related research lack the ability to generate…

Artificial Intelligence · Computer Science 2023-08-15 Yuhe Nie , Shaoming Zheng , Zhan Zhuang , Xuan Song

Goal-conditioned reinforcement learning (GCRL), related to a set of complex RL problems, trains an agent to achieve different goals under particular scenarios. Compared to the standard RL solutions that learn a policy solely depending on…

Artificial Intelligence · Computer Science 2022-09-05 Minghuan Liu , Menghui Zhu , Weinan Zhang

Goal-Conditioned Reinforcement Learning (GCRL) provides a versatile framework for developing unified controllers capable of handling wide ranges of tasks, exploring environments, and adapting behaviors. However, its reliance on…

Machine Learning · Computer Science 2025-02-20 Charly Pecqueux-Guézénec , Stéphane Doncieux , Nicolas Perrin-Gilbert

Machine learning has been a popular tool in many different fields, including procedural content generation. However, procedural content generation via machine learning (PCGML) approaches can struggle with controllability and coherence. In…

Machine Learning · Computer Science 2021-07-28 Kynan Sorochan , Jerry Chen , Yakun Yu , Matthew Guzdial

Recent advances in video world modeling have enabled large-scale generative models to simulate embodied environments with high visual fidelity, providing strong priors for prediction, planning, and control. Yet, despite their realism, these…

Computer Vision and Pattern Recognition · Computer Science 2026-02-10 Haoyang He , Jay Patrikar , Dong-Ki Kim , Max Smith , Daniel McGann , Ali-akbar Agha-mohammadi , Shayegan Omidshafiei , Sebastian Scherer

In neural video codecs, current state-of-the-art methods typically adopt multi-scale motion compensation to handle diverse motions. These methods estimate and compress either optical flow or deformable offsets to reduce inter-frame…

Multimedia · Computer Science 2024-12-03 Yongqi Zhai , Jiayu Yang , Wei Jiang , Chunhui Yang , Luyang Tang , Ronggang Wang

We propose a hierarchical entity-centric framework for offline Goal-Conditioned Reinforcement Learning (GCRL) that combines subgoal decomposition with factored structure to solve long-horizon tasks in domains with multiple entities.…

Machine Learning · Computer Science 2026-02-04 Dan Haramati , Carl Qi , Tal Daniel , Amy Zhang , Aviv Tamar , George Konidaris