mlsanityData to 14 Oct 2026

Automated Play-Testing Through RL Based Human-Like Play-Styles Generation

arXiv 2211.17188 ↗First posted 29 Nov 2022cs.LG cs.AIcited by 11

Not on the map. Why?

Abstract (arXiv)

The increasing complexity of gameplay mechanisms in modern video games is leading to the emergence of a wider range of ways to play games. The variety of possible play-styles needs to be anticipated by designers, through automated tests. Reinforcement Learning is a promising answer to the need of automating video game testing. To that effect one needs to train an agent to play the game, while ensuring this agent will generate the same play-styles as the players in order to give meaningful feedback to the designers. We present CARMI: a Configurable Agent with Relative Metrics as Input. An agent able to emulate the players play-styles, even on previously unseen levels. Unlike current methods it does not rely on having full trajectories, but only summary data. Moreover it only requires little human data, thus compatible with the constraints of modern video game production. This novel agent could be used to investigate behaviors and balancing during the production of a video game with a realistic amount of training time.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Builds on 13 of its 27 references that are in the map. First posted on arXiv 29 Nov 2022.

Builds on

13 of 27 references.

References · 13

  1. 2015Prioritized Experience Replaycited by 1,099
  2. 2018Unity: A General Platform for Intelligent Agentscited by 236
  3. 2016Sample Efficient Actor-Critic with Experience Replaycited by 188
  4. 2020Automatic Curriculum Learning For Deep RL: A Short Surveycited by 150
  5. 2021Goal-Conditioned Reinforcement Learning with Imagined Subgoalscited by 134
  6. 2019Teacher algorithms for curriculum learning of Deep RL in continuously parameterized environmentscited by 119
  7. 2021Modeling Strong and Human-Like Gameplay with KL-Regularized Searchcited by 50
  8. 2021Augmenting Automated Game Testing with Deep Reinforcement Learningcited by 38
  9. 2021Direct Behavior Specification via Constrained Reinforcement Learningcited by 31
  10. 2018Automated Playtesting with Procedural Personas through MCTS with Evolved Heuristicscited by 28
  11. 2020Deep Reinforcement Learning for Navigation in AAA Video Gamescited by 27
  12. 2022CCPT: Automatic Gameplay Testing and Validation with Curiosity-Conditioned Proximal Trajectoriescited by 6
1 more
  1. 2017Inverse Reinforcement Learning from Summary Datacited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 3; 2024: 0; 2025: 3; 2026: 5.

11 papers.

  1. 2023Mechanic Maker 2.0: Reinforcement Learning for Evaluating Generated Rulescited by 4
  2. 2023Towards Human-Like RL: Taming Non-Naturalistic Behavior in Deep RL via Adaptive Behavioral Costs in 3D Gamescited by 4
  3. 2023Adversarial Imitation Learning On Aggregated Datacited by 1
  4. 2025Cultivating Game Sense for Yourself: Making VLMs Gaming Expertscited by 1
  5. 2025A modular framework for automated evaluation of procedural content generation in serious games with deep reinforcement learning agentscited by 0
  6. 2025UBCL: A Reinforcement Learning Framework for Controllable and Diverse Player Behaviorscited by 0
  7. 2026Robo-Saber: Generating and Simulating Virtual Reality Playerscited by 0
  8. 2026CA2: Code-Aware Agent for Automated Game Testingcited by 0
  9. 2026Coachable agents for interactive gameplaycited by 0
  10. 2026Reward-Adaptive Iterative Discovery: A Case Study on Automated Game Testing for NHL26cited by 0
  11. 2026Comparative Analysis of GAT and BERT for Human-Like Playtestingcited by 0