Related papers: Penalization Framework For Autonomous Agents Using…

Behavioral skills or policies for autonomous agents are conventionally learned from reward functions, via reinforcement learning, or from demonstrations, via imitation learning. However, both modes of task specification have their…

Agents in real-world scenarios like automated driving deal with uncertainty in their environment, in particular due to perceptual uncertainty. Although, reinforcement learning is dedicated to autonomous decision-making under uncertainty…

Designing an effective communication mechanism among agents in reinforcement learning has been a challenging task, especially for real-world applications. The number of agents can grow or an environment sometimes needs to interact with a…

We propose a framework for adaptive data-centric collaborative machine learning among self-interested agents, coordinated by an arbiter. Designed to handle the incremental nature of real-world data, the framework operates in an online…

Principled accountability for autonomous decision-making in uncertain environments requires distinguishing intentional outcomes from negligent designs from actual accidents. We propose analyzing the behavior of autonomous agents through a…

In this paper, we propose a framework for solving a single-agent task by using multiple agents, each focusing on different aspects of the task. This approach has two main advantages: 1) it allows for training specialized agents on different…

We consider a network of autonomous agents whose outputs are actions in a game with coupled constraints. In such network scenarios, agents seeking to minimize coupled cost functions using distributed information while satisfying the coupled…

In this paper we present a Reinforcement Learning environment that leverages agent cooperation and communication, aimed at detection, learning and ultimately penalizing betrayal patterns that emerge in the behavior of self-interested…

Autonomous agent systems increasingly trigger real-world side effects: deploying infrastructure, modifying databases, moving money, and executing workflows. Yet most agent stacks provide no mandatory execution checkpoint where organizations…

In autonomous navigation, a planning system reasons about other agents to plan a safe and plausible trajectory. Before planning starts, agents are typically processed with computationally intensive models for recognition, tracking, motion…

Training a model-free reinforcement learning agent requires allowing the agent to sufficiently explore the environment to search for an optimal policy. In safety-constrained environments, utilizing unsupervised exploration or a non-optimal…

Deep Reinforcement Learning has been shown to be very successful in complex games, e.g. Atari or Go. These games have clearly defined rules, and hence allow simulation. In many practical applications, however, interactions with the…

Cybersecurity decision-making increasingly occurs in environments characterized by uncertainty, partial observability, and adversarial manipulation, where heterogeneous signals from multiple sources are often incomplete, ambiguous, or…

Autonomous AI agents can remain fully authorized and still become unsafe as behavior drifts, adversaries adapt, and decision patterns shift without any code change. We propose the \textbf{Informational Viability Principle}: governing an…

The concepts of blameworthiness and wrongness are of fundamental importance in human moral life. But to what extent are humans disposed to blame artificially intelligent agents, and to what extent will they judge their actions to be morally…

Reinforcement learning (RL) agents with pre-specified reward functions cannot provide guaranteed safety across variety of circumstances that an uncertain system might encounter. To guarantee performance while assuring satisfaction of safety…

Fraud can pose a challenge in many resource allocation domains, including social service delivery and credit provision. For example, agents may misreport private information in order to gain benefits or access to credit. To mitigate this, a…

We propose an agent-based framework for personalized filtering of categorized harassing communication in online social networks. Unlike global moderation systems that apply uniform filtering rules, our approach models user-specific…

The intent of control argumentation frameworks is to specifically model strategic scenarios from the perspective of an agent by extending the standard model of argumentation framework in a way that takes unquantified uncertainty regarding…

Automating scientific computing workflows requires more than generating executable code: autonomous systems must also select appropriate computational strategies, implement them faithfully, and ensure that the resulting outcomes remain…