What is GameAI™?GameAI is an AI suite of instruments designed to help you leverage accurate and unbiased game testing & balancing as well as a real-time personalisation of level complexity and content for your players to give them the best fully customized experience in your game. To show the impact and predict future transactions we connect balancing and game content usage parameters with revenue and retention metrics.
Who is GameAI™ intended for?Game developers who are looking to search for ways of improving user experience, securing high engagement rates, and maximizing retention to meet financial goals and accelerate revenue.
What are AI Agents?AI Agents are virtual agents taught and trained with the help of Reinforcement Learning to achieve different goals, from beating the game, performing a unique set of tasks, enhancing gameplay immersion, to helping improve the gaming development experience and balance, including retention and monetization. In short, AI Agents can be used for:
- Game Testing & Balancing
- Personalization of game content for different player categories
- Level Design
- Deep understanding of gameplay and improvement paths
- Automated QA
- Automated Content Generation
- And much more.
- Reinforcement Learning
How does GameAI™ work and what technology does it use?We apply Reinforcement Learning, as well as other Machine Learning algorithms like generative adversarial networks and clustering algorithms to model multiple diverse scenarios for balancing the game and content generation, user behaviour, retention and revenue prediction. Such a cocktail of RL and ML is selected to achieve the best possible results as it provides us with the necessary artificial intelligence to be able to mimic real users behaviour and decision making and by aligning with the major monetization trends provide personalized well balanced game content in real-time which leads to critical game metrics increase. Predicting in-game and ad revenue is performed by another set of ML algorithms.
What is the productivity of AI Agents?AI Agents help save up to 70% of game development time.
Does the GameAI substitute human playtesting 100%?Yes.
- Testing and balancing
How do we train AI Agents?To train AI agents efficiently, we developed a unified training pipeline. Here’s the 3-step pipeline:
Determine the action space. These actions can be discrete, like pressing a button or continuous as in the value within an interval. Actions can be as many as you’d like to have performed simultaneously, and keep in mind that some actions can be invalid under specific conditions.
Determine the reward. The reward must correspond to the goal we want to accomplish—for example, a positive reward when winning and a negative reward when losing. You can also give a positive reward for each action that leads to a target or a negative reward when moving far away from the target.
Define the Deep Reinforcement Learning algorithm. The speed of the agent’s learning capabilities depends on the algorithm as well as whether the agent can learn at all. For each task, it’s necessary to study the features and how applicable they are in unique contexts.
How much time is needed to train an agent?To train AI agents efficiently it takes around two hours.
How much time is needed to playtest and balance?Up to 1-15 minutes per 10 - 100 levels
What is the value-add of GameAI?GameAI drives profits by using reinforcement learning to accelerate testing with AI Agents, yield precise and unbiased results, provide optimal balance for players, determine the best move sequences, exploits, and solutions, and give a centralized overview of analytics and metrics for seamless control.
What kinds of games can benefit from GameAI?Nearly all game genres can benefit from GameAI™ as it accelerates high-quality, personalized content development and it assesses gameplay bottlenecks by a large number of metrics. Primarily designed for highly variable games, games with a developed economy, puzzles, logic games, procedurally generated worlds, etc. Human-like avatars run thousands of plays at a time and are not biased which achieves high accuracy results.