Related papers: Rapid Skill Capture in a First-Person Shooter
Users often interpret and select agent skills through their SKILL markdown specifications. To protect users, existing audits mainly focus on malicious or unsafe skills. We study the complementary question of whether specifications help…
eSports industry has greatly progressed within the last decade in terms of audience and fund rising, broadcasting, networking and hardware. Since the number and quality of professional team has evolved too, there is a reasonable need in…
Guessing games are a prototypical instance of the "learning by interacting" paradigm. This work investigates how well an artificial agent can benefit from playing guessing games when later asked to perform on novel NLP downstream tasks such…
Except for special classes of games, there is no systematic framework for analyzing the dynamical properties of multi-agent strategic interactions. Potential games are one such special but restrictive class of games that allow for tractable…
To help evaluate and understand the latent capabilities of language models, this paper introduces an approach using optimized input embeddings, or 'soft prompts,' as a metric of conditional distance between a model and a target behavior.…
Algorithms that generate computer game content require game design knowledge. We present an approach to automatically learn game design knowledge for level design from gameplay videos. We further demonstrate how the acquired design…
This article explores the value and measurable effects of hard and soft skills in academia when teaching and developing abilities for the game industry. As we discuss, each individuals engagement with the subject directly impacts their…
CLIP (Contrastive Language-Image Pretraining) is an efficient method for learning computer vision tasks from natural language supervision that has powered a recent breakthrough in deep learning due to its zero-shot transfer capabilities. By…
Self-supervised learning has emerged as a method for utilizing massive unlabeled data for pre-training models, providing an effective feature extractor for various mobile sensing applications. However, when deployed to end-users, these…
Skill-based reinforcement learning (RL) has emerged as a promising strategy to leverage prior knowledge for accelerated robot learning. Skills are typically extracted from expert demonstrations and are embedded into a latent space from…
Agent skills today are static artifact: authored once -- by human curation or one-shot generation from parametric knowledge -- and then consumed unchanged, with no mechanism to improve from real use. We propose \textbf{SkillEvolver}, a…
In order to deploy autonomous agents to domains such as autonomous driving, infrastructure management, health care, and finance, they must be able to adapt safely to unseen situations. The current approach in constructing such agents is to…
Cyber defence exercises are intensive, hands-on learning events for teams of professionals who gain or develop their skills to successfully prevent and respond to cyber attacks. The exercises mimic the real-life, routine operation of an…
Text-to-image generation models represent the next step of evolution in image synthesis, offering a natural way to achieve flexible yet fine-grained control over the result. One emerging area of research is the fast adaptation of large…
Learning new task-specific skills from a few trials is a fundamental challenge for artificial intelligence. Meta reinforcement learning (meta-RL) tackles this problem by learning transferable policies that support few-shot adaptation to…
Assistive machines endow people with limited mobility the opportunity to live more independently. However, operating these machines poses risks to the safety of the human operator as well as the surrounding environment. Thus, proper user…
We study a collaborative scenario where a user not only instructs a system to complete tasks, but also acts alongside it. This allows the user to adapt to the system abilities by changing their language or deciding to simply accomplish some…
This paper explores the estimation of user attention in the setting of a cooperative handheld robot: a robot designed to behave as a handheld tool but that has levels of task knowledge. We use a tool-mounted gaze tracking system, which,…
Most of the players have experienced the feeling of temporarily losing their character in a given gameplay situation when they cannot control the character, simply because they temporarily cannot see it. The main reasons for this feeling…
User's intentions may be expressed through spontaneous gesturing, which have been seen only a few times or never before. Recognizing such gestures involves one shot gesture learning. While most research has focused on the recognition of the…