Related papers: Multi-Agent Empowerment and Emergence of Complex B…

In this paper, we identify a radically new viewpoint on the collective behaviour of groups of intelligent agents. We first develop a highly general abstract model for the possible future lives that these agents may encounter as a result of…

Advances in artificial intelligence often stem from the development of new environments that abstract real-world situations into a form where research can be done conveniently. This paper contributes such an environment based on ideas…

The reinforcement learning paradigm allows, in principle, for complex behaviours to be learned directly from simple reward signals. In practice, however, it is common to carefully hand-design the reward function to encourage a particular…

We propose a model of collective behavior in self-propelled active agents that incorporates a perceptual decision-making process. In this framework, the decision-making dynamics is modeled using quantum formalism. The perceptual decision…

Animating and simulating crowds using an agent-based approach is a well-established area where every agent in the crowd is individually controlled such that global human-like behaviour emerges. We observe that human navigation and movement…

Intrinsic rewards have been increasingly used to mitigate the sparse reward problem in single-agent reinforcement learning. These intrinsic rewards encourage the agent to look for novel experiences, guiding the agent to explore the…

A local culture denotes a commonly shared behaviour within a cluster of firms. Similar to social norms or conventions, it is an emergent feature resulting from the firms' interaction in an economic network. To model these dynamics, we…

Multi-agent systems composed of large generative models are rapidly moving from laboratory prototypes to real-world deployments, where they jointly plan, negotiate, and allocate shared resources to solve complex tasks. While such systems…

The enactive approach to cognition is typically proposed as a viable alternative to traditional cognitive science. Enactive cognition displaces the explanatory focus from the internal representations of the agent to the direct sensorimotor…

In many scenarios, a principal dynamically interacts with an agent and offers a sequence of incentives to align the agent's behavior with a desired objective. This paper focuses on the problem of synthesizing an incentive sequence that,…

We study emergent communication in a multi-agent reinforcement learning setting, where the agents solve cooperative tasks and have access to a communication channel. The communication channel may consist of either discrete symbols or…

Humans are interactive agents driven to seek out situations with interesting physical dynamics. Here we formalize the functional form of physical intrinsic motivation. We first collect ratings of how interesting humans find a variety of…

In this work, we ask for and answer what makes classical temporal-difference reinforcement learning with epsilon-greedy strategies cooperative. Cooperating in social dilemma situations is vital for animals, humans, and machines. While…

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…

Traditional evolutionary game theory describes how certain strategy spreads throughout the system where individual player imitates the most successful strategy among its neighborhood. Accordingly, player doesn't have own authority to change…

Infants explore their complex physical and social environment in an organized way. To gain insight into what intrinsic motivations may help structure this exploration, we create a virtual infant agent and place it in a…

The significance of network structures in promoting group cooperation within social dilemmas has been widely recognized. Prior studies attribute this facilitation to the assortment of strategies driven by spatial interactions. Although…

Active inference helps us simulate adaptive behavior and decision-making in biological and artificial agents. Building on our previous work exploring the relationship between active inference, well-being, resilience, and sustainability, we…

Multi-agent systems - systems with multiple independent AI agents working together to achieve a common goal - are becoming increasingly prevalent in daily life. Drawing inspiration from the phenomenon of human group social influence, we…

Empowerment quantifies the influence an agent has on its environment. This is formally achieved by the maximum of the expected KL-divergence between the distribution of the successor state conditioned on a specific action and a distribution…