In the rapidly evolving field of large language models (LLMs), data augmentation (DA) has
emerged as a pivotal technique for enhancing model performance by diversifying training …

Large language models (LLMs) hold interesting potential for the design, development, and
research of video games. Building on the decades of prior research on generative AI in …

Reinforcement learning from human feedback (RLHF) is a variant of reinforcement learning
(RL) that learns from human feedback instead of relying on an engineered reward function …

This manuscript gives a big-picture, up-to-date overview of the field of (deep) reinforcement
learning and sequential decision making, covering value-based RL, policy-gradient …

Automatically generating novel and interesting games is a complex task. Challenges include
representing game rules in a computationally workable form, searching through the large …

Reinforcement Learning (RL), bolstered by the expressive capabilities of Deep Neural
Networks (DNNs) for function approximation, has demonstrated considerable success in …

Conventional state representations in reinforcement learning often omit critical task-related
details, presenting a significant challenge for value networks in establishing accurate …

Large Language Models (LLMs) and Vision Language Models (VLMs) possess extensive
knowledge and exhibit promising reasoning abilities; however, they still struggle to perform …

The development of game agents holds a critical role in advancing towards Artificial General
Intelligence (AGI). The progress of LLMs and their multimodal counterparts (MLLMs) offers …

Language Models (LMs) offer an exciting solution for general-purpose embodied control.
However, a key technical issue arises when using an LM-based controller: environment …