Related papers: Parametrically Retargetable Decision-Makers Tend T…
AI systems have become increasingly capable of dangerous behaviours in many domains. This raises the question: Do models sometimes choose to violate human instructions in order to perform behaviour that is more useful for certain goals? We…
Humans and animals solve a difficult problem much more easily when they are presented with a sequence of problems that starts simple and slowly increases in difficulty. We explore this idea in the context of reinforcement learning. Rather…
We describe AI agents as stochastic dynamical systems and frame the problem of learning to reason as in transductive inference: Rather than approximating the distribution of past data as in classical induction, the objective is to capture…
Recent advances in deep learning have brought attention to the possibility of creating advanced, general AI systems that outperform humans across many tasks. However, if these systems pursue unintended goals, there could be catastrophic…
Many important behavior changes are frictionful; they require individuals to expend effort over a long period with little immediate gratification. Here, an artificial intelligence (AI) agent can provide personalized interventions to help…
Unlike reinforcement learning (RL) agents, humans remain capable multitaskers in changing environments. In spite of only experiencing the world through their own observations and interactions, people know how to balance focusing on tasks…
Our goal is for agents to optimize the right reward function, despite how difficult it is for us to specify what that is. Inverse Reinforcement Learning (IRL) enables us to infer reward functions from demonstrations, but it usually assumes…
We study the problem of agent selection in causal strategic learning under multiple decision makers and address two key challenges that come with it. Firstly, while much of prior work focuses on studying a fixed pool of agents that remains…
This paper proposes a suite of rationality measures and associated theory for reinforcement learning agents, a property increasingly critical yet rarely explored. We define an action in deployment to be perfectly rational if it maximises…
Assistive agents should make humans' lives easier. Classically, such assistance is studied through the lens of inverse reinforcement learning, where an assistive agent (e.g., a chatbot, a robot) infers a human's intention and then selects…
We consider the problem of reinforcement learning when provided with (1) a baseline control policy and (2) a set of constraints that the learner must satisfy. The baseline policy can arise from demonstration data or a teacher agent and may…
Humans are spectacular reinforcement learners, constantly learning from and adjusting to experience and feedback. Unfortunately, this doesn't necessarily mean humans are fast learners. When tasks are challenging, learning can become…
A long-term goal of reinforcement learning is to design agents that can autonomously interact and learn in the world. A critical challenge to such autonomy is the presence of irreversible states which require external assistance to recover…
Recent developments in sequential experimental design look to construct a policy that can efficiently navigate the design space, in a way that maximises the expected information gain. Whilst there is work on achieving tractable policies for…
AI systems often rely on two key components: a specified goal or reward function and an optimization algorithm to compute the optimal behavior for that goal. This approach is intended to provide value for a principal: the user on whose…
Customizing robotic behaviors to be aligned with diverse human preferences is an underexplored challenge in the field of embodied AI. In this paper, we present Promptable Behaviors, a novel framework that facilitates efficient…
We address the problem of learning to assign prediction tasks to one agent from a set of available human or AI agents. In particular, we focus on the sequential learning of agent expertise and assignment policies where each agent is…
Researchers have demonstrated that Deep Reinforcement Learning (DRL) is a powerful tool for finding policies that perform well on complex robotic systems. However, these policies are often unpredictable and can induce highly variable…
Agentic AIs $-$ AIs that are capable and permitted to undertake complex actions with little supervision $-$ mark a new frontier in AI capabilities and raise new questions about how to safely create and align such systems with users,…
In the future, artificial learning agents are likely to become increasingly widespread in our society. They will interact with both other learning agents and humans in a variety of complex settings including social dilemmas. We consider the…