mlsanityData to 14 Oct 2026

IPCGRL: Language-Instructed Reinforcement Learning for Procedural Level Generation

arXiv 2503.12358 ↗First posted 16 Mar 2025cs.AI cs.CL cs.LGcited by 4

On the map: Deep reinforcement learning methods → RL training of language and agent models

Abstract (arXiv)

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, research on deep reinforcement learning (DRL) agents utilizing text-based instructions for procedural content generation remains limited. In this paper, we propose IPCGRL, an instruction-based procedural content generation method via reinforcement learning, which incorporates a sentence embedding model. IPCGRL fine-tunes task-specific embedding representations to effectively compress game-level conditions. We evaluate IPCGRL in a two-dimensional level generation task and compare its performance with a general-purpose embedding method. The results indicate that IPCGRL achieves up to a 21.4% improvement in controllability and a 17.2% improvement in generalizability for unseen instructions. Furthermore, the proposed method extends the modality of conditional input, enabling a more flexible and expressive interaction framework for procedural content generation.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Placed in RL training of language and agent models, one of 15 directions in Deep reinforcement learning methods. Builds on 22 of its 27 references that are in the map. First posted on arXiv 16 Mar 2025.

Builds on

22 of 27 references.

References · 22

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2017Proximal Policy Optimization Algorithmscited by 15,215
  3. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,348
  4. 2020Language Conditioned Imitation Learning over Unstructured Datacited by 209
  5. 2021Multi-Task Reinforcement Learning with Context-based Representationscited by 174
  6. 2017Procedural Content Generation via Machine Learning (PCGML)cited by 137
  7. 2019Using Natural Language for Reward Shaping in Reinforcement Learningcited by 114
  8. 2022Discovered Policy Optimisationcited by 104
  9. 2020PCGRL: Procedural Content Generation via Reinforcement Learningcited by 90
  10. 2018Learning to Understand Goal Specifications by Modelling Rewardcited by 80
  11. 2023Language Instructed Reinforcement Learning for Human-AI Coordinationcited by 63
  12. 2021Learning Controllable Content Generatorscited by 40
10 more
  1. 2023Goal Representations for Instruction Following: A Semi-Supervised Language Interface to Controlcited by 32
  2. 2022Learning Controllable 3D Level Generatorscited by 19
  3. 2022Meta-Reinforcement Learning via Language Instructionscited by 18
  4. 2024Language Grounded Multi-agent Reinforcement Learning with Human-interpretable Communicationcited by 17
  5. 2023RaidEnv: Exploring New Challenges in Automated Content Balancing for Boss Raid Gamescited by 7
  6. 2024PCGRL+: Scaling, Control and Generalization in Reinforcement Learning Level Generatorscited by 7
  7. 2021Arachnophobia Exposure Therapy using Experience-driven Procedural Content Generation via Reinforcement Learning (EDPCGRL)cited by 5
  8. 2024ChatPCG: Large Language Model-Driven Reward Design for Procedural Content Generationcited by 5
  9. 2024G-PCGRL: Procedural Graph Data Generation via Reinforcement Learningcited by 4
  10. 2025PCGRLLM: Large Language Model-Driven Reward Design for Procedural Content Generation Reinforcement Learningcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 2.

4 papers.

  1. 2025Multi-Objective Instruction-Aware Representation Learning in Procedural Content Generation RLcited by 3
  2. 2025Human-Aligned Procedural Level Generation Reinforcement Learning via Text-Level-Sketch Shared Representationcited by 2
  3. 2026Multiverse: Language-Conditioned Multi-Game Level Blending via Shared Representationcited by 1
  4. 2026Select-to-Act: Hierarchical Reinforcement Learning via Adaptive Language Guidancecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Video Game Level Design as a Multi-Agent Reinforcement Learning Problem
  2. 2024STARLING: Self-supervised Training of Text-based Reinforcement Learning Agent with Large Language Models
  3. 2024Instruction Following with Goal-Conditioned Reinforcement Learning in Virtual Environments
  4. 2025PARL: Prompt-based Agents for Reinforcement Learning
  5. 2026Progressive Agent Skill Generation via Reinforcement Learning
  6. 2026SKILLER: Language-Level Reinforcement Learning for Reusable Skill Extraction in Small Language Models
  7. 2024GLIDE-RL: Grounded Language Instruction through DEmonstration in RL
  8. 2022Is Reinforcement Learning (Not) for Natural Language Processing: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimization