Related papers: NAIL: A General Interactive Fiction Agent
Recent years have seen an increasing amount of work on embodied AI agents that can perform tasks by following human language instructions. However, most of these agents are reactive, meaning that they simply learn and imitate behaviors…
Proactive and real-time interactive experiences are essential for human-like AI companions, yet face three key challenges: (1) achieving low-latency inference under continuous streaming inputs, (2) autonomously deciding when to respond, and…
This paper presents a computational account of how legal norms can influence the behavior of artificial intelligence (AI) agents, grounded in the active inference framework (AIF) that is informed by principles of economic legal analysis…
In recent years, Hypergraph Neural Networks (HNNs) have demonstrated immense potential in handling complex systems with high-order interactions. However, acquiring large-scale, high-quality labeled data for these models is costly, making…
This paper summarizes the AAIA'17 Data Mining Challenge: Helping AI to Play Hearthstone which was held between March 23, and May 15, 2017 at the Knowledge Pit platform. We briefly describe the scope and background of this competition in the…
The swift evolution of Large-scale Models (LMs), either language-focused or multi-modal, has garnered extensive attention in both academy and industry. But despite the surge in interest in this rapidly evolving area, there are scarce…
We show that a critical vulnerability in adversarial imitation is the tendency of discriminator networks to learn spurious associations between visual features and expert labels. When the discriminator focuses on task-irrelevant features,…
Fictitious play is an algorithm for computing Nash equilibria of matrix games. Recently, machine learning variants of fictitious play have been successfully applied to complicated real-world games. This paper presents a simple modification…
Current Graphical User Interface (GUI) agents operate primarily under a reactive paradigm: a user must provide an explicit instruction for the agent to execute a task. However, an intelligent AI assistant should be proactive, which is…
Agent performance is strongly shaped by the surrounding harness: the external execution system around a model that organizes a task run. Yet this logic is usually buried in tightly coupled controller code, which makes harnesses hard to…
This paper is both an introduction and an invitation. It is an introduction to CARLE, a Life-like cellular automata simulator and reinforcement learning environment. It is also an invitation to Carle's Game, a challenge in open-ended…
The growing adoption of large language models (LLMs) presents potential for deeper understanding of human behaviours within game theory frameworks. Addressing research gap on multi-player competitive games, this paper examines the strategic…
Agentic AI systems can now generate code with remarkable fluency, but a fundamental question remains: \emph{does the generated code actually do what the user intended?} The gap between informal natural language requirements and precise…
We have observed significant progress in visual navigation for embodied agents. A common assumption in studying visual navigation is that the environments are static; this is a limiting assumption. Intelligent navigation may involve…
In this paper, we present a new methodology that employs tester agents to automate video game testing. We introduce two types of agents -synthetic and human-like- and two distinct approaches to create them. Our agents are derived from…
Adversarial imitation learning (AIL), a prominent approach in imitation learning, has achieved significant practical success powered by neural network approximation. However, existing theoretical analyses of AIL are primarily confined to…
Human intelligence exhibits a remarkable capacity for rapid adaptation and effective problem-solving in novel and unfamiliar contexts. We argue that this profound adaptability is fundamentally linked to the efficient construction and…
AI agents have been evaluated in isolation or within small groups, where interactions remain limited in scope and complexity. Large-scale simulations involving many autonomous agents -- reflecting the full spectrum of civilizational…
This paper presents the research on the interdisciplinary research infrastructure for understanding human reasoning in game-theoretic terms. Strategic reasoning is considered to impact human decision making in social, economical and…
Autonomous driving (AD) requires safe and reliable decision-making among interacting agents, e.g., vehicles, bicycles, and pedestrians. Multi-agent reinforcement learning (MARL) modeled by Markov games (MGs) provides a suitable framework to…