Conference

3D Building Generation in Minecraft via Large Language Models

Recently, procedural content generation has exhibited considerable advancements in the domain of 2D game level generation such as Super Mario Bros. and Sokoban through large language models (LLMs). To further validate the capabilities of LLMs, this …

Higher Replay Ratio Empowers Sample-Efficient Multi-Agent Reinforcement Learning

One of the notorious issues for Reinforcement Learning (RL) is poor sample efficiency. Compared to single agent RL, the sample efficiency for Multi-Agent Reinforcement Learning (MARL) is more challenging because of its inherent partial observability, …

DanZero: Mastering GuanDan Game with Reinforcement Learning

The use of artificial intelligence (AI) in card games has been a widely researched topic in the field of AI for an extended period. Recent advancements have led to AI programs exhibiting expert-level gameplay in complex card games such as Mahjong, …

Compressing and Comparing the Generative Spaces of Procedural Content Generators

The past decade has seen a rapid increase in the level of research interest in procedural content generation (PCG) for digital games, and there are now numerous research avenues focused on new approaches for driving and applying PCG systems. An area …

A generalizability measure for program synthesis with genetic programming

The generalizability of programs synthesized by genetic programming (GP) to unseen test cases is one of the main challenges of GP-based program synthesis. Recent work showed that increasing the amount of training data improves the generalizability of …

Genetic Adversarial Training of Decision Trees

We put forward a novel learning methodology for ensembles of decision trees based on a genetic algorithm that is able to train a decision tree for maximizing both its accuracy and its robustness to adversarial perturbations. This learning algorithm …

Model Learning with Personalized Interpretability Estimation (ML-PIE)

High-stakes applications require AI-generated models to be interpretable. Current algorithms for the synthesis of potentially interpretable models rely on objectives or regularization terms that represent interpretability only coarsely (e.g., model …

DAE-GP: denoising autoencoder LSTM networks as probabilistic models in estimation of distribution genetic programming

Estimation of distribution genetic programming (EDA-GP) algorithms are metaheuristics where sampling new solutions from a learned probabilistic model replaces the standard mutation and recombination operators of genetic programming (GP). This paper …

Synthesis through unification genetic programming

We present a new method, Synthesis through Unification Genetic Programming (STUN GP), which synthesizes provably correct programs using a Divide and Conquer approach. This method first splits the input space by undergoing a discovery phase that uses …

Communication in Decision Making: Competition favors Inequality

We consider a multi-agent system in which the individual goal is to collect resources, but where the amount of collected resources depends also on others decision. Agents can communicate and can take advantage of being communicated other agents' …