Related papers: A unified strategy for implementing curiosity and …
One of the remarkable feats of intelligent life is that it restructures the world it lives in for its own benefit. This extended abstract outlines how the information-theoretic principle of empowerment, as an intrinsic motivation, can be…
We consider a setting for Inverse Reinforcement Learning (IRL) where the learner is extended with the ability to actively select multiple environments, observing an agent's behavior on each environment. We first demonstrate that if the…
We introduce a class of learning problems where the agent is presented with a series of tasks. Intuitively, if there is relation among those tasks, then the information gained during execution of one task has value for the execution of…
How do you incentivize self-interested agents to $\textit{explore}$ when they prefer to $\textit{exploit}$? We consider complex exploration problems, where each agent faces the same (but unknown) MDP. In contrast with traditional…
We revisit the role of instrumental value as a driver of adaptive behavior. In active inference, instrumental or extrinsic value is quantified by the information-theoretic surprisal of a set of observations measuring the extent to which…
Autonomous navigation in crowded environments is an open problem with many applications, essential for the coexistence of robots and humans in the smart cities of the future. In recent years, deep reinforcement learning approaches have…
Learning about many things can provide numerous benefits to a reinforcement learning system. For example, learning many auxiliary value functions, in addition to optimizing the environmental reward, appears to improve both exploration and…
The reinforcement learning (RL) research area is very active, with an important number of new contributions; especially considering the emergent field of deep RL (DRL). However a number of scientific and technical challenges still need to…
Learning to control an environment without hand-crafted rewards or expert data remains challenging and is at the frontier of reinforcement learning research. We present an unsupervised learning algorithm to train agents to achieve…
Recently, AI systems have made remarkable progress in various tasks. Deep Reinforcement Learning(DRL) is an effective tool for agents to learn policies in low-level state spaces to solve highly complex tasks. Researchers have introduced…
Understanding how artificial agents model internal mental states is central to advancing Theory of Mind in AI. Evidence points to a unified system for self- and other-awareness. We explore this self-awareness by having reinforcement…
What is the nature of curiosity? Is there any scientific way to understand the origin of this mysterious force that drives the behavior of even the stupidest naturally intelligent systems and is completely absent in their smartest…
This paper studies the optimal mechanism to motivate effort in a dynamic principal-agent model without transfers. An agent is engaged in a task with uncertain future rewards and can quit at any time. The principal knows the reward and…
Advancements in reinforcement learning have produced a variety of complex and useful intrinsic driving forces; crucially, these drivers operate under a direct conditioning paradigm. This form of conditioning limits our agents' capacity by…
Curiosity is a vital metacognitive skill in educational contexts. Yet, little is known about how social factors influence curiosity in group work. We argue that curiosity is evoked not only through individual, but also interpersonal…
Imitation can be viewed as a means of enhancing learning in multiagent environments. It augments an agent's ability to learn useful behaviors by making intelligent use of the knowledge implicit in behaviors demonstrated by cooperative…
End-to-end multi-task dialogue systems are usually designed with separate modules for the dialogue pipeline. Among these, the policy module is essential for deciding what to do in response to user input. This policy is trained by…
We introduce an exploration bonus for deep reinforcement learning methods calculated using self-organising feature maps. Our method uses adaptive resonance theory (ART) providing online, unsupervised clustering to quantify the novelty of a…
Power-seeking behavior is a key source of risk from advanced AI, but our theoretical understanding of this phenomenon is relatively limited. Building on existing theoretical results demonstrating power-seeking incentives for most reward…
We describe a simple scheme that allows an agent to learn about its environment in an unsupervised manner. Our scheme pits two versions of the same agent, Alice and Bob, against one another. Alice proposes a task for Bob to complete; and…