mlsanityData to 14 Oct 2026

A Model-Driven Approach for Developing Families of Reinforcement Learning Environments

arXiv 2606.20324 ↗First posted 18 Jun 2026cs.SE cs.LGcited by 0

On the map: Deep reinforcement learning methods → Deep RL algorithms and representations

Abstract (arXiv)

Virtual training environments are software-intensive systems in which reinforcement learning (RL) agents learn, adapt, and demonstrate meaningful behavior. Virtual training environments offer a safe and cost-efficient alternative to training agents in real-world settings. However, to converge, most realistic RL problems require training in multiple, mostly similar but slightly different environments - i.e., families of environment variants. The typical development process of environment families is a labor-intensive and error-prone manual endeavor that does not scale well. To alleviate these issues, in this paper, we propose a model-driven approach for developing families of RL training environments. To obtain the family of environments, we develop an approach and prototype tool. In our approach, a hybrid genetic algorithm - a combination of population-based global search and heuristic local search - generates environment families. Mutations and constraints are expressed as model transformations and are operationalized into a search process by a state-of-the-art model transformation engine. We demonstrate the soundness of our approach in a wildfire mitigation scenario and curriculum learning - a particular learning paradigm that relies on environment families.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Deep RL algorithms and representations, one of 15 directions in Deep reinforcement learning methods. Builds on 26 of its 79 references that are in the map. First posted on arXiv 18 Jun 2026.

Builds on

26 of 79 references.

Closest ancestors · 3

Same direction, newest first

  1. 2026A Reference Architecture of Reinforcement Learning Frameworks6 Mar
  2. 2025Meta-World+: An Improved, Standardized, RL Benchmark16 May
  3. 2024Towards a Domain-Specific Modelling Environment for Reinforcement Learning12 Oct

Other references · 23

  1. 2019Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learningcited by 1,204
  2. 2021Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learningcited by 998
  3. 2018Learning Dexterous In-Hand Manipulationcited by 687
  4. 2019Leveraging Procedural Generation to Benchmark Reinforcement Learningcited by 483
  5. 2021Towards Out-Of-Distribution Generalization: A Surveycited by 436
  6. 2020Sim-to-Real Transfer in Deep Reinforcement Learning for Robotics: a Surveycited by 413
  7. 2020Curriculum Learning for Reinforcement Learning Domains: A Framework and Surveycited by 373
  8. 2020Emergent Complexity and Zero-shot Transfer via Unsupervised Environment Designcited by 275
  9. 2021Curriculum Learning: A Surveycited by 259
  10. 2020PettingZoo: Gym for Multi-Agent Reinforcement Learningcited by 220
  11. 2017Teacher-Student Curriculum Learningcited by 210
  12. 2017Reverse Curriculum Generation for Reinforcement Learningcited by 198
11 more
  1. 2021Multi-Task Reinforcement Learning with Context-based Representationscited by 174
  2. 2024AgentGen: Enhancing Planning Abilities for Large Language Model based Agent via Environment and Task Generationcited by 83
  3. 2023How Simulation Helps Autonomous Driving:A Survey of Sim2real, Digital Twins, and Parallel Intelligencecited by 58
  4. 2021When Is Generalizable Reinforcement Learning Tractable?cited by 20
  5. 2024Eurekaverse: Environment Curriculum Generation via Large Language Modelscited by 16
  6. 2020Sim-to-Real Transfer with Incremental Environment Complexity for Reinforcement Learning of Depth-Based Robot Navigationcited by 13
  7. 2022Robust Reinforcement Learning via Genetic Curriculumcited by 10
  8. 2023Model-driven Engineering for Machine Learning Components: A Systematic Literature Reviewcited by 7
  9. 2023When to Trust AI: Advances and Challenges for Certification of Neural Networkscited by 6
  10. 2025AI Simulation by Digital Twins: Systematic Survey, Reference Framework, and Mapping to a Standardized Architecturecited by 6
  11. 2025Complex Model Transformations by Reinforcement Learning with Uncertain Human Guidancecited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Parental Guidance: Efficient Lifelong Learning through Evolutionary Distillation
  2. 2024Enabling Adaptive Agent Training in Open-Ended Simulators by Targeting Diversity
  3. 2025Distilling Reinforcement Learning Algorithms for In-Context Model-Based Planning
  4. 2026From Trainee to Trainer: LLM-Designed Training Environment for RL with Multi-Agent Reasoning
  5. 2026Environment Evolution for Terminal Agents
  6. 2026Autonomous Continual Learning for Environment Adaptation of Computer-Use Agents
  7. 2025AutoForge: Automated Environment Synthesis for Agentic Reinforcement Learning
  8. 2024Ancestral Reinforcement Learning: Unifying Zeroth-Order Optimization and Genetic Algorithms for Reinforcement Learning