Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- research-articleMay 2024
A Survey of Multi-Agent Deep Reinforcement Learning with Communication
AAMAS '24: Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent SystemsPages 2845–2847Communication 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 ...
- research-articleMay 2024
pgeon applied to Overcooked-AI to explain agents' behaviour
AAMAS '24: Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent SystemsPages 2821–2823Policy 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 ...
- research-articleMay 2024
Toward Explainable Agent Behaviour
AAMAS '24: Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent SystemsPages 2740–2742Agents 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 ...
- extended-abstractMay 2024
Decision Market Based Learning for Multi-agent Contextual Bandit Problems
AAMAS '24: Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent SystemsPages 2549–2551Information 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 ...
- extended-abstractMay 2024
Unifying Regret and State-Action Space Coverage for Effective Unsupervised Environment Design
AAMAS '24: Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent SystemsPages 2507–2509Unsupervised 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 ...
-
- extended-abstractMay 2024
Neurological Based Timing Mechanism for Reinforcement Learning
AAMAS '24: Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent SystemsPages 2504–2506The 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 ...
- extended-abstractMay 2024
GOV-REK: Governed Reward Engineering Kernels for Designing Robust Multi-Agent Reinforcement Learning Systems
AAMAS '24: Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent SystemsPages 2429–2431For 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 ...
- extended-abstractMay 2024
Emergent Dominance Hierarchies in Reinforcement Learning Agents
AAMAS '24: Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent SystemsPages 2426–2428Modern 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 ...
- extended-abstractMay 2024
Time-Constrained Restless Multi-Armed Bandits with Applications to City Service Scheduling
AAMAS '24: Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent SystemsPages 2375–2377Municipalities 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 ...
- extended-abstractMay 2024
ELA: Exploited Level Augmentation for Offline Learning in Zero-Sum Games
AAMAS '24: Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent SystemsPages 2357–2359Offline 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-...
- extended-abstractMay 2024
Addressing Permutation Challenges in Multi-Agent Reinforcement Learning
AAMAS '24: Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent SystemsPages 2303–2305In 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 ...
- research-articleMay 2024
Emergent Cooperation under Uncertain Incentive Alignment
AAMAS '24: Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent SystemsPages 1521–1530Understanding 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 ...
- research-articleMay 2024
Grasper: A Generalist Pursuer for Pursuit-Evasion Problems
AAMAS '24: Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent SystemsPages 1147–1155Pursuit-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 ...
- research-articleMay 2024
Higher Order Reasoning under Intent Uncertainty Reinforces the Hobbesian Trap
AAMAS '24: Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent SystemsPages 1066–1074Civilisations 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 ...
- research-articleMay 2024
Analysing the Sample Complexity of Opponent Shaping
AAMAS '24: Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent SystemsPages 623–631Learning 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 ...
- research-articleMay 2024
Potential-Based Reward Shaping for Intrinsic Motivation
AAMAS '24: Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent SystemsPages 589–597Recently 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 ...
- research-articleMay 2024
Learning and Calibrating Heterogeneous Bounded Rational Market Behaviour with Multi-agent Reinforcement Learning
AAMAS '24: Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent SystemsPages 534–543Agent-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-...
- research-articleMay 2024
Reinforcement Learning in the Wild with Maximum Likelihood-based Model Transfer
AAMAS '24: Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent SystemsPages 516–524In 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 ...
- research-articleMay 2024
Boosting Continuous Control with Consistency Policy
AAMAS '24: Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent SystemsPages 335–344Due 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 ...
- research-articleMay 2024
Deep Anomaly Detection via Active Anomaly Search
AAMAS '24: Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent SystemsPages 308–316Anomaly 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 ...