Related papers: Mitigating Negative Side Effects via Environment S…

The idea that a group of cooperating agents can solve problems more efficiently than when those agents work independently is hardly controversial, despite our obliviousness of the conditions that make cooperation a successful problem…

Machine learning systems have been widely used to make decisions about individuals who may behave strategically to receive favorable outcomes, e.g., they may genuinely improve the true labels or manipulate observable features directly to…

Policies often fail due to distribution shift -- changes in the state and reward that occur when a policy is deployed in new environments. Data augmentation can increase robustness by making the model invariant to task-irrelevant changes in…

For effective human-agent teaming, robots and other artificial intelligence (AI) agents must infer their human partner's abilities and behavioral response patterns and adapt accordingly. Most prior works make the unrealistic assumption that…

Reinforcement Learning (RL) algorithms can learn robotic control tasks from visual observations, but they often require a large amount of data, especially when the visual scene is complex and unstructured. In this paper, we explore how the…

The rapid rise of Artificial Intelligence (AI) is reshaping Software Engineering (SE), creating new opportunities while introducing human-centered challenges. Although prior work notes behavioral and other non-technical factors in AI…

We introduce environment predictive coding, a self-supervised approach to learn environment-level representations for embodied agents. In contrast to prior work on self-supervised learning for images, we aim to jointly encode a series of…

We study the benefits of reinforcement learning (RL) environments based on agent-based models (ABM). While ABMs are known to offer microfoundational simulations at the cost of computational complexity, we empirically show in this work that…

Reinforcement learning solutions have great success in the 2-player general sum setting. In this setting, the paradigm of Opponent Shaping (OS), in which agents account for the learning of their co-players, has led to agents which are able…

To successfully tackle challenging manipulation tasks, autonomous agents must learn a diverse set of skills and how to combine them. Recently, self-supervised agents that set their own abstract goals by exploiting the discovered structure…

We train embodied agents to play Visual Hide and Seek where a prey must navigate in a simulated environment in order to avoid capture from a predator. We place a variety of obstacles in the environment for the prey to hide behind, and we…

Reinforcement learning (RL) agents are commonly trained and evaluated in the same environment. In contrast, humans often train in a specialized environment before being evaluated, such as studying a book before taking an exam. The potential…

Implicit feedback is widely explored by modern recommender systems. Since the feedback is often sparse and imbalanced, it poses great challenges to the learning of complex interactions among users and items. Metric learning has been…

This paper proposes to leverage the emerging~learning techniques and devise a multi-agent online source {seeking} algorithm under unknown environment. Of particular significance in our problem setups are: i) the underlying environment is…

Context and motivation. Requirements Engineering (RE) quality still lacks empirical evidence on how specific requirement defects affect downstream activities. Problem: However, empirical data on the detailed effects of requirements quality…

Computational agents support humans in many areas of life and are therefore found in heterogeneous contexts. This means they operate in rapidly changing environments and can be confronted with huge state and action spaces. In order to…

We study the problem of teaching via demonstrations in sequential decision-making tasks. In particular, we focus on the situation when the teacher has no access to the learner's model and policy, and the feedback from the learner is limited…

In highly interactive driving scenes, trajectory prediction is conditioned on information from surrounding traffic participants such as cars and pedestrians. Our main contribution is a comprehensive analysis of state-of-the-art trajectory…

Trained human pilots or operators still stand out through their efficient, robust, and versatile skills in guidance tasks such as driving agile vehicles in spatial environments or performing complex surgeries. This research studies how…

This article proposes a fundamental methodological shift in the modelling of policy interventions for sustainability transitions in order to account for complexity (e.g. self-reinforcing mechanism arising from multi-agent interactions) and…