Related papers: Fast Peer Adaptation with Context-aware Exploratio…
Parameter sharing, as an important technique in multi-agent systems, can effectively solve the scalability issue in large-scale agent problems. However, the effectiveness of parameter sharing largely depends on the environment setting. When…
Reinforcement Learning (RL) agents often struggle with inefficient exploration, particularly in environments with sparse rewards. Traditional exploration strategies can lead to slow learning and suboptimal performance because agents fail to…
Serendipity-oriented recommender systems expose users to unfamiliar items to counter filter bubbles, yet mere exposure does not ensure that users will understand or appreciate the content they encounter. We propose Peer Recommendation, a…
Mutual relationships, such as cooperation and exploitation, are the basis of human and other biological societies. The foundations of these relationships are rooted in the decision making of individuals, and whether they choose to be…
A generic property of biological, social and economical networks is their ability to evolve in time, creating and suppressing interactions. We approach this issue within the framework of an adaptive network of agents playing a Prisoner's…
We study allocation problems without monetary transfers where agents have correlated types, i.e., hold private information about one another. Such peer information is relevant in various settings, including science funding, allocation of…
An open problem in evolutionary game dynamics is to understand the effect of peer pressure on cooperation in a quantitative manner. Peer pressure can be modeled by punishment, which has been proved to be an effective mechanism to sustain…
The game of Codenames has recently emerged as a domain of interest for intelligent agent design. The game is unique due to the way that language and coordination between teammates play important roles. Previous approaches to designing…
The key challenge in multiagent learning is learning a best response to the behaviour of other agents, which may be non-stationary: if the other agents adapt their strategy as well, the learning target moves. Disparate streams of research…
AI agents negotiate and transact in natural language with unfamiliar counterparts: a buyer bot facing an unknown seller, or a procurement assistant negotiating with a supplier. In such interactions, the counterpart's LLM, prompts, control…
Researchers have demonstrated that neural networks are vulnerable to adversarial examples and subtle environment changes, both of which one can view as a form of distribution shift. To humans, the resulting errors can look like blunders,…
In an adversarial environment, a hostile player performing a task may behave like a non-hostile one in order not to reveal its identity to an opponent. To model such a scenario, we define identity concealment games: zero-sum stochastic…
In repeated games, such as auctions, players rely on autonomous learning agents to choose their actions. We study settings in which players have their agents make monetary transfers to other agents during play at their own expense, in order…
Large language models (LLMs) demonstrate strong reasoning abilities across mathematical, strategic, and linguistic tasks, yet little is known about how well they reason in dynamic, real-time, multi-agent scenarios, such as collaborative…
We study the policy evaluation problem in an online multi-reward multi-policy discounted setting, where multiple reward functions must be evaluated simultaneously for different policies. We adopt an $(\epsilon,\delta)$-PAC perspective to…
We are interested in studying how heterogeneous agents can learn to communicate and cooperate with each other without being explicitly pre-programmed to do so. Motivated by this goal, we present and analyze a distributed solution to a…
Adapting an agent's behaviour to new environments has been one of the primary focus areas of physics based reinforcement learning. Although recent approaches such as universal policy networks partially address this issue by enabling the…
Peer-To-Peer (P2P) networks are self-organizing, distributed systems, with no centralized authority or infrastructure. Because of the voluntary participation, the availability of resources in a P2P system can be highly variable and…
The ability to continuously learn and adapt to new situations is one where humans are far superior compared to AI agents. We propose an approach to knowledge transfer using behavioural strategies as a form of transferable knowledge…
Multi-agent reinforcement learning has received significant interest in recent years notably due to the advancements made in deep reinforcement learning which have allowed for the developments of new architectures and learning algorithms.…