PCGRL: Procedural Content Generation via Reinforcement Learning

2020-01-24 · Ahmed Khalifa, Philip Bontrager, Sam Earle, Julian Togelius

We investigate how reinforcement learning can be used to train level-designing agents. This represents a new approach to procedural content generation in games, where level design is framed as a game, and the content generator itself is learned. By seeing the design problem as a sequential task, we can use reinforcement learning to learn how to take the next action so that the expected final level quality is maximized. This approach can be used when few or no examples exist to train from, and the trained generator is very fast. We investigate three different ways of transforming two-dimensional level design problems into Markov decision processes and apply these to three game environments.

📄 PDF Abstract BibTeX arXiv:2001.09212

Code (6)

amidos2006/gym-pcgrl 공식 구현 tf

SnDehghani/pcgrl_d_m tf

amidos2006/marahel

poi233/pcgrl_rts tf

smearle/control-pcgrl tf

smearle/gym-pcgrl tf

Tasks

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

IPCGRL: Language-Instructed Reinforcement Learning for Procedural Level Generation

2025-03-16 · In-Chang Baek, Sung-Hyun Kim, Seo-Young Lee, Dong-Hyeon Kim 외

Recent research has highlighted the significance of natural language in enhancing the controllability of generative models. While various efforts have been made to leverage natural language for content generation, resear…

Deep Reinforcement Learning reinforcement-learning Reinforcement Learning Sentence+2

G-PCGRL: Procedural Graph Data Generation via Reinforcement Learning

2024-07-15 · Florian Rupp, Kai Eckert

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, g…

reinforcement-learning Reinforcement Learning

Human-Aligned Procedural Level Generation Reinforcement Learning via Text-Level-Sketch Shared Representation

2025-08-13 · In-Chang Baek, Seoyoung Lee, Sung-Hyun Kim, Geumhwan Hwang 외 arxiv

Human-aligned AI is a critical component of co-creativity, as it enables models to accurately interpret human intent and generate controllable outputs that align with design goals in collaborative content creation. This …

Reinforcement Learning Contrastive Learning

Multi-Objective Instruction-Aware Representation Learning in Procedural Content Generation RL

2025-08-08 · Sung-Hyun Kim, Geum-Hwan Hwang, In-Chang Baek, Seo-Young Lee 외 arxiv

Recent advancements in generative modeling emphasize the importance of natural language as a highly expressive and accessible modality for controlling content generation. However, existing instructed reinforcement learni…

Multi-Label Classification Representation Learning Reinforcement Learning

Arachnophobia Exposure Therapy using Experience-driven Procedural Content Generation via Reinforcement Learning (EDPCGRL)

2021-10-07 · Athar Mahmoudi-Nejad, Matthew Guzdial, Pierre Boulanger

Personalized therapy, in which a therapeutic practice is adapted to an individual patient, leads to better health outcomes. Typically, this is accomplished by relying on a therapist's training and intuition along with fe…

reinforcement-learning Reinforcement Learning (RL)