Linus Gisslén

Alessandro Sestini, Joakim Bergdahl, Konrad Tollmar et al.

In games, as in and many other domains, design validation and testing is a huge challenge as systems are growing in size and manual testing is becoming infeasible. This paper proposes a new approach to automated game validation and testing. Our method leverages a data-driven imitation learning technique, which requires little effort and time and no knowledge of machine learning or programming, that designers can use to efficiently train game testing agents. We investigate the validity of our approach through a user study with industry experts. The survey results show that our method is indeed a valid approach to game validation and that data-driven programming would be a useful aid to reducing effort and increasing quality of modern playtesting. The survey also highlights several open challenges. With the help of the most recent literature, we analyze the identified challenges and propose future research directions suitable for supporting and maximizing the utility of our approach.

William Ahlberg, Alessandro Sestini, Konrad Tollmar et al.

Reinforcement learning has been widely successful in producing agents capable of playing games at a human level. However, this requires complex reward engineering, and the agent's resulting policy is often unpredictable. Going beyond reinforcement learning is necessary to model a wide range of human playstyles, which can be difficult to represent with a reward function. This paper presents a novel imitation learning approach to generate multiple persona policies for playtesting. Multimodal Generative Adversarial Imitation Learning (MultiGAIL) uses an auxiliary input parameter to learn distinct personas using a single-agent model. MultiGAIL is based on generative adversarial imitation learning and uses multiple discriminators as reward models, inferring the environment reward by comparing the agent and distinct expert policies. The reward from each discriminator is weighted according to the auxiliary input. Our experimental analysis demonstrates the effectiveness of our technique in two environments with continuous and discrete action spaces.

Matilda Tamm, Olivia Shamon, Hector Anadon Leon et al.

Modern video games are rapidly growing in size and scale, and to create rich and interesting environments, a large amount of content is needed. As a consequence, often several thousands of detailed 3D assets are used to create a single scene. As each asset's polygon mesh can contain millions of polygons, the number of polygons that need to be drawn every frame may exceed several billions. Therefore, the computational resources often limit how many detailed objects that can be displayed in a scene. To push this limit and to optimize performance one can reduce the polygon count of the assets when possible. Basically, the idea is that an object at farther distance from the capturing camera, consequently with relatively smaller screen size, its polygon count may be reduced without affecting the perceived quality. Level of Detail (LOD) refers to the complexity level of a 3D model representation. The process of removing complexity is often called LOD reduction and can be done automatically with an algorithm or by hand by artists. However, this process may lead to deterioration of the visual quality if the different LODs differ significantly, or if LOD reduction transition is not seamless. Today the validation of these results is mainly done manually requiring an expert to visually inspect the results. However, this process is slow, mundane, and therefore prone to error. Herein we propose a method to automate this process based on the use of deep convolutional networks. We report promising results and envision that this method can be used to automate the process of LOD reduction testing and validation.

Monica Villanueva Aylagas, Joakim Bergdahl, Jonas Gillberg et al.

Generative models for level generation have shown great potential in game production. However, they often provide limited control over the generation, and the validity of the generated levels is unreliable. Despite this fact, only a few approaches that learn from existing data provide the users with ways of controlling the generation, simultaneously addressing the generation of unsolvable levels. %One of the main challenges it faces is that levels generated through automation may not be solvable thus requiring validation. are not always engaging, challenging, or even solvable. This paper proposes Avalon, a novel method to improve models that learn from existing level designs using difficulty statistics extracted from gameplay. In particular, we use a conditional variational autoencoder to generate layouts for match-3 levels, conditioning the model on pre-collected statistics such as game mechanics like difficulty and relevant visual features like size and symmetry. Our method is general enough that multiple approaches could potentially be used to generate these statistics. We quantitatively evaluate our approach by comparing it to an ablated model without difficulty conditioning. Additionally, we analyze both quantitatively and qualitatively whether the style of the dataset is preserved in the generated levels. Our approach generates more valid levels than the same method without difficulty conditioning.

Derek Yadgaroff, Alessandro Sestini, Konrad Tollmar et al.

Imitation learning is an effective approach for training game-playing agents and, consequently, for efficient game production. However, generalization - the ability to perform well in related but unseen scenarios - is an essential requirement that remains an unsolved challenge for game AI. Generalization is difficult for imitation learning agents because it requires the algorithm to take meaningful actions outside of the training distribution. In this paper we propose a solution to this challenge. Inspired by the success of data augmentation in supervised learning, we augment the training data so the distribution of states and actions in the dataset better represents the real state-action distribution. This study evaluates methods for combining and applying data augmentations to observations, to improve generalization of imitation learning agents. It also provides a performance benchmark of these augmentations across several 3D environments. These results demonstrate that data augmentation is a promising framework for improving generalization in imitation learning agents.

Ruoqi Zhang, Ziwei Luo, Jens Sjölund et al.

Diffusion models have shown impressive performance in capturing complex and multi-modal action distributions for game agents, but their slow inference speed prevents practical deployment in real-time game environments. While consistency models offer a promising approach for one-step generation, they often suffer from training instability and performance degradation when applied to policy learning. In this paper, we present CPQE (Consistency Policy with Q-Ensembles), which combines consistency models with Q-ensembles to address these challenges.CPQE leverages uncertainty estimation through Q-ensembles to provide more reliable value function approximations, resulting in better training stability and improved performance compared to classic double Q-network methods. Our extensive experiments across multiple game scenarios demonstrate that CPQE achieves inference speeds of up to 60 Hz -- a significant improvement over state-of-the-art diffusion policies that operate at only 20 Hz -- while maintaining comparable performance to multi-step diffusion approaches. CPQE consistently outperforms state-of-the-art consistency model approaches, showing both higher rewards and enhanced training stability throughout the learning process. These results indicate that CPQE offers a practical solution for deploying diffusion-based policies in games and other real-time applications where both multi-modal behavior modeling and rapid inference are critical requirements.

Amir Baghi, Jens Sjölund, Joakim Bergdahl et al.

Multi-agent reinforcement learning has shown promise in learning cooperative behaviors in team-based environments. However, such methods often demand extensive training time. For instance, the state-of-the-art method TiZero takes 40 days to train high-quality policies for a football environment. In this paper, we hypothesize that better exploration mechanisms can improve the sample efficiency of multi-agent methods. We propose two different approaches for better exploration in TiZero: a self-supervised intrinsic reward and a random network distillation bonus. Additionally, we introduce architectural modifications to the original algorithm to enhance TiZero's computational efficiency. We evaluate the sample efficiency of these approaches through extensive experiments. Our results show that random network distillation improves training sample efficiency by 18.8% compared to the original TiZero. Furthermore, we evaluate the qualitative behavior of the models produced by both variants against a heuristic AI, with the self-supervised reward encouraging possession and random network distillation leading to a more offensive performance. Our results highlights the applicability of our random network distillation variant in practical settings. Lastly, due to the nature of the proposed method, we acknowledge its use beyond football simulation, especially in environments with strong multi-agent and strategic aspects.

Alessandro Sestini, Joakim Bergdahl, Jean-Philippe Barrette-LaPierre et al.

While several high profile video games have served as testbeds for Deep Reinforcement Learning (DRL), this technique has rarely been employed by the game industry for crafting authentic AI behaviors. Previous research focuses on training super-human agents with large models, which is impractical for game studios with limited resources aiming for human-like agents. This paper proposes a sample-efficient DRL method tailored for training and fine-tuning agents in industrial settings such as the video game industry. Our method improves sample efficiency of value-based DRL by leveraging pre-collected data and increasing network plasticity. We evaluate our method training a goalkeeper agent in EA SPORTS FC 25, one of the best-selling football simulations today. Our agent outperforms the game's built-in AI by 10% in ball saving rate. Ablation studies show that our method trains agents 50% faster compared to standard DRL methods. Finally, qualitative evaluation from domain experts indicates that our approach creates more human-like gameplay compared to hand-crafted agents. As a testament to the impact of the approach, the method has been adopted for use in the most recent release of the series.

António Afonso, Iolanda Leite, Alessandro Sestini et al.

Reinforcement Learning (RL) in games has gained significant momentum in recent years, enabling the creation of different agent behaviors that can transform a player's gaming experience. However, deploying RL agents in production environments presents two key challenges: (1) designing an effective reward function typically requires an RL expert, and (2) when a game's content or mechanics are modified, previously tuned reward weights may no longer be optimal. Towards the latter challenge, we propose an automated approach for iteratively fine-tuning an RL agent's reward function weights, based on a user-defined language based behavioral goal. A Language Model (LM) proposes updated weights at each iteration based on this target behavior and a summary of performance statistics from prior training rounds. This closed-loop process allows the LM to self-correct and refine its output over time, producing increasingly aligned behavior without the need for manual reward engineering. We evaluate our approach in a racing task and show that it consistently improves agent performance across iterations. The LM-guided agents show a significant increase in performance from $9\%$ to $74\%$ success rate in just one iteration. We compare our LM-guided tuning against a human expert's manual weight design in the racing task: by the final iteration, the LM-tuned agent achieved an $80\%$ success rate, and completed laps in an average of $855$ time steps, a competitive performance against the expert-tuned agent's peak $94\%$ success, and $850$ time steps.

Alessandro Sestini, Joakim Bergdahl, Konrad Tollmar et al.

In offline reinforcement learning, agents are trained using only a fixed set of stored transitions derived from a source policy. However, this requires that the dataset be labeled by a reward function. In applied settings such as video game development, the availability of the reward function is not always guaranteed. This paper proposes Trajectory-Ranked OFfline Inverse reinforcement learning (TROFI), a novel approach to effectively learn a policy offline without a pre-defined reward function. TROFI first learns a reward function from human preferences, which it then uses to label the original dataset making it usable for training the policy. In contrast to other approaches, our method does not require optimal trajectories. Through experiments on the D4RL benchmark we demonstrate that TROFI consistently outperforms baselines and performs comparably to using the ground truth reward to learn policies. Additionally, we validate the efficacy of our method in a 3D game environment. Our studies of the reward model highlight the importance of the reward function in this setting: we show that to ensure the alignment of a value function to the actual future discounted reward, it is fundamental to have a well-engineered and easy-to-learn reward function.

Joakim Bergdahl, Alessandro Sestini, Linus Gisslén

In strategy games, one of the most important aspects of game design is maintaining a sense of challenge for players. Many mobile titles feature quick gameplay loops that allow players to progress steadily, requiring an abundance of levels and puzzles to prevent them from reaching the end too quickly. As with any content creation, testing and validation are essential to ensure engaging gameplay mechanics, enjoyable game assets, and playable levels. In this paper, we propose an automated approach that can be leveraged for gameplay testing and validation that combines traditional scripted methods with reinforcement learning, reaping the benefits of both approaches while adapting to new situations similarly to how a human player would. We test our solution on a popular tower defense game, Plants vs. Zombies. The results show that combining a learned approach, such as reinforcement learning, with a scripted AI produces a higher-performing and more robust agent than using only heuristic AI, achieving a 57.12% success rate compared to 47.95% in a set of 40 levels. Moreover, the results demonstrate the difficulty of training a general agent for this type of puzzle-like game.

Leonardo Marini, Linus Gisslén, Alessandro Sestini

In games, and more generally in the field of software development, early detection of bugs is vital to maintain a high quality of the final product. Automated tests are a powerful tool that can catch a problem earlier in development by executing periodically. As an example, when new code is submitted to the code base, a new automated test verifies these changes. However, identifying the specific change responsible for a test failure becomes harder when dealing with batches of changes -- especially in the case of a large-scale project such as a AAA game, where thousands of people contribute to a single code base. This paper proposes a new approach to automatically identify which change in the code caused a test to fail. The method leverages Large Language Models (LLMs) to associate error messages with the corresponding code changes causing the failure. We investigate the effectiveness of our approach with quantitative and qualitative evaluations. Our approach reaches an accuracy of 71% in our newly created dataset, which comprises issues reported by developers at EA over a period of one year. We further evaluated our model through a user study to assess the utility and usability of the tool from a developer perspective, resulting in a significant reduction in time -- up to 60% -- spent investigating issues.

Alessandro Sestini, Linus Gisslén, Joakim Bergdahl et al.

This paper proposes a novel deep reinforcement learning algorithm to perform automatic analysis and detection of gameplay issues in complex 3D navigation environments. The Curiosity-Conditioned Proximal Trajectories (CCPT) method combines curiosity and imitation learning to train agents to methodically explore in the proximity of known trajectories derived from expert demonstrations. We show how CCPT can explore complex environments, discover gameplay issues and design oversights in the process, and recognize and highlight them directly to game designers. We further demonstrate the effectiveness of the algorithm in a novel 3D navigation environment which reflects the complexity of modern AAA video games. Our results show a higher level of coverage and bug discovery than baselines methods, and it hence can provide a valuable tool for game designers to identify issues in game design automatically.

Joakim Bergdahl, Camilo Gordillo, Konrad Tollmar et al.

General game testing relies on the use of human play testers, play test scripting, and prior knowledge of areas of interest to produce relevant test data. Using deep reinforcement learning (DRL), we introduce a self-learning mechanism to the game testing framework. With DRL, the framework is capable of exploring and/or exploiting the game mechanics based on a user-defined, reinforcing reward signal. As a result, test coverage is increased and unintended game play mechanics, exploits and bugs are discovered in a multitude of game types. In this paper, we show that DRL can be used to increase test coverage, find exploits, test map difficulty, and to detect common problems that arise in the testing of first-person shooter (FPS) games.

Camilo Gordillo, Joakim Bergdahl, Konrad Tollmar et al.

As modern games continue growing both in size and complexity, it has become more challenging to ensure that all the relevant content is tested and that any potential issue is properly identified and fixed. Attempting to maximize testing coverage using only human participants, however, results in a tedious and hard to orchestrate process which normally slows down the development cycle. Complementing playtesting via autonomous agents has shown great promise accelerating and simplifying this process. This paper addresses the problem of automatically exploring and testing a given scenario using reinforcement learning agents trained to maximize game state coverage. Each of these agents is rewarded based on the novelty of its actions, thus encouraging a curious and exploratory behaviour on a complex 3D scenario where previously proposed exploration techniques perform poorly. The curious agents are able to learn the complex navigation mechanics required to reach the different areas around the map, thus providing the necessary data to identify potential issues. Moreover, the paper also explores different visualization strategies and evaluates how to make better use of the collected data to drive design decisions and to recognize possible problems and oversights.

Linus Gisslén, Andy Eakins, Camilo Gordillo et al.

We present a new approach ARLPCG: Adversarial Reinforcement Learning for Procedural Content Generation, which procedurally generates and tests previously unseen environments with an auxiliary input as a control variable. Training RL agents over novel environments is a notoriously difficult task. One popular approach is to procedurally generate different environments to increase the generalizability of the trained agents. ARLPCG instead deploys an adversarial model with one PCG RL agent (called Generator) and one solving RL agent (called Solver). The Generator receives a reward signal based on the Solver's performance, which encourages the environment design to be challenging but not impossible. To further drive diversity and control of the environment generation, we propose using auxiliary inputs for the Generator. The benefit is two-fold: Firstly, the Solver achieves better generalization through the Generator's generated challenges. Secondly, the trained Generator can be used as a creator of novel environments that, together with the Solver, can be shown to be solvable. We create two types of 3D environments to validate our model, representing two popular game genres: a third-person platformer and a racing game. In these cases, we shows that ARLPCG has a significantly better solve ratio, and that the auxiliary inputs renders the levels creation controllable to a certain degree. For a video compilation of the results please visit https://youtu.be/z7q2PtVsT0I.

Jack Harmer, Linus Gisslén, Jorge del Val et al.

In this work we describe a novel deep reinforcement learning architecture that allows multiple actions to be selected at every time-step in an efficient manner. Multi-action policies allow complex behaviours to be learnt that would otherwise be hard to achieve when using single action selection techniques. We use both imitation learning and temporal difference (TD) reinforcement learning (RL) to provide a 4x improvement in training time and 2.5x improvement in performance over single action selection TD RL. We demonstrate the capabilities of this network using a complex in-house 3D game. Mimicking the behavior of the expert teacher significantly improves world state exploration and allows the agents vision system to be trained more rapidly than TD RL alone. This initial training technique kick-starts TD learning and the agent quickly learns to surpass the capabilities of the expert.