Communication is an effective mechanism for coordinating the behaviors of multiple agents, broadening their views of the environment, and to support their collaborations. In the field of multi-agent deep reinforcement learning (MADRL), agents can improve ...

Policy Graphs (PGs) are a method for representing the behaviour of opaque agents by observing them in the environment and producing graphs where the state and action spaces are discretised into predicates. We present pgeon, a Python library that ...

Agents are a special kind of AI-based software in that they interact in complex environments and have increased potential for emergent behaviour, even in isolation. Explaining such behaviour is key to deploying trustworthy AI, but the increasing ...

Information is often stored in a distributed and proprietary form, and agents who own this information are often self-interested and require incentives to reveal it. Suitable mechanisms are required to elicit and aggregate such distributed information ...

Unsupervised Environment Design (UED) employs interactive training between a teacher agent and a student agent to train generally-capable student agents. Existing UED methods primarily rely on regret to progressively introduce curriculum complexity for ...

The inherently time-dependent dynamics which underly the neuronal spiking communication, are ubquitous throughout brain, and yet are not fully understood. Likewise time-based mechanisms are underdeveloped in the field of Machine and Reinforcement ...

For multi-agent reinforcement learning (MARL) systems, the problem task often involves massive problem-specific reward engineering effort. This effort is usually not directly transferable to other problems; worse, this problem is further exacerbated for ...

Modern Reinforcement Learning (RL) algorithms are able to outperform humans in a wide variety of tasks. Multi-agent reinforcement learning (MARL) settings present additional challenges around cooperation in mixed-motive groups. Social conventions and ...

Municipalities maintain critical infrastructure through inspections, both proactive and in response to complaints. For example, the Chicago Department of Public Health (CDPH) periodically inspects 7000 food establishments to maintain the safety of food ...

Offline learning derives effective policies from expert demonstrators' datasets without direct interaction. While recent research consider dataset characteristics like expertise level or multiple demonstrators, a distinct approach is necessary in zero-...

In Reinforcement Learning, deep neural networks play a crucial role, especially in Multi-Agent Systems. Owing to information from multiple sources, the challenge lies in handling input permutations efficiently, causing sample inefficiency and delayed ...

Understanding the emergence of cooperation in systems of computational agents is crucial for the development of effective cooperative AI. Interaction among individuals in real-world settings are often sparse and occur within a broad spectrum of ...

Pursuit-evasion games (PEGs) model interactions between a team of pursuers and an evader in graph-based environments such as urban street networks. Recent advancements have demonstrated the effectiveness of the pre-training and fine-tuning paradigm in ...

Civilisations in the universe face the difficulty of communicating and trying to understand others' intentions. Moreover, advanced civilisations could develop weapons to pre-emptively eliminate any civilisations that present a future threat - this is ...

Learning in general-sum games often yields collectively sub-optimal results. Addressing this, opponent shaping (OS) methods actively guide the learning processes of other agents, empirically leading to improved individual and group performances. Early OS ...

Recently there has been a proliferation of intrinsic motivation (IM) reward-shaping methods to learn in complex and sparse-reward environments. These methods can often inadvertently change the set of optimal policies in an environment, leading to ...

Agent-based models (ABMs) have shown promise for modelling various real world phenomena incompatible with traditional equilibrium analysis. However, a critical concern is the manual definition of behavioural rules in ABMs. Recent developments in multi-...

In this paper, we study the problem of transferring the available Markov Decision Process (MDP) models to learn and plan efficiently in an unknown but similar MDP. We refer to it as Model Transfer Reinforcement Learning (MTRL) problem. First, we ...

Due to its training stability and strong expression, the diffusion model has attracted considerable attention in offline reinforcement learning. However, several challenges have also come with it: 1) The demand for a large number of diffusion steps makes ...

Anomaly detection (AD) holds substantial practical value, and considering the limited labeled data, the semi-supervised anomaly detection technique has garnered increasing attention. We find that previous methods suffer from insufficient exploitation of ...