Imitation learning is an effective approach for training game-playing agents and, consequently, for efficient game production.
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.
Going from research to production, especially for large and complex software systems, is fundamentally a hard problem.
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.
Focusing on Random Forests, we propose a multi-armed contextual bandit recommendation framework for feature-based selection of a single shallow tree of the learned ensemble.
This paper proposes a novel deep reinforcement learning algorithm to perform automatic analysis and detection of gameplay issues in complex 3D navigation environments.
To this end, we propose four different policy fusion methods for combining pre-trained policies.
Recent advances in Deep Reinforcement Learning (DRL) have largely focused on improving the performance of agents with the aim of replacing humans in known and well-defined environments.
We propose a technique based on Adversarial Inverse Reinforcement Learning which can significantly decrease the need for expert demonstrations in PCG games.
In this paper we introduce DeepCrawl, a fully-playable Roguelike prototype for iOS and Android in which all agents are controlled by policy networks trained using Deep Reinforcement Learning (DRL).