相关论文: BOLT: Online Lightweight Adaptation for Preparatio…

Multi-agent systems often require agents to collaborate with or compete against other agents with diverse goals, behaviors, or strategies. Agent modeling is essential when designing adaptive policies for intelligent machine agents in…

Parameter-efficient tuning (PET) methods such as LoRA, Adapter, and Visual Prompt Tuning (VPT) have found success in enabling adaptation to new domains by tuning small modules within a transformer model. However, the number of domains…

We present RefPtsFusion, a lightweight and interpretable framework for cooperative autonomous driving. Instead of sharing large feature maps or query embeddings, vehicles exchange compact reference points, e.g., objects' positions,…

Cooperative perception is a promising technique for intelligent and connected vehicles through vehicle-to-everything (V2X) cooperation, provided that accurate pose information and relative pose transforms are available. Nevertheless,…

We introduce Emergent Trust Learning (ETL), a lightweight, trust-based control algorithm that can be plugged into existing AI agents. It enables these to reach cooperation in competitive game environments under shared resources. Each agent…

We propose a novel method for training deep neural networks that are capable of interpolation, that is, driving the empirical loss to zero. At each iteration, our method constructs a stochastic approximation of the learning objective. The…

Learning a latent dynamics model provides a task-agnostic representation of an agent's understanding of its environment. Leveraging this knowledge for model-based reinforcement learning (RL) holds the potential to improve sample efficiency…

Recently, adapting pre-trained models to downstream tasks has attracted increasing interest. Previous Parameter-Efficient-Tuning (PET) methods regard the pre-trained model as an opaque Black Box model, relying purely on data-driven…

The use of reinforcement learning to dynamically adapt and evade detection is now well-documented in several cybersecurity settings including Covert Social Influence Operations (CSIOs), in which bots try to spread disinformation. While AI…

Successful deployment of multi-agent reinforcement learning often requires agents to adapt their behaviour. In this work, we discuss the problem of teamwork adaptation in which a team of agents needs to adapt their policies to solve novel…

Existing multi-agent perception algorithms usually select to share deep neural features extracted from raw sensing data between agents, achieving a trade-off between accuracy and communication bandwidth limit. However, these methods assume…

Collaborative perception has been proven to improve individual perception in autonomous driving through multi-agent interaction. Nevertheless, most methods often assume identical encoders for all agents, which does not hold true when these…

Differentiable simulation has become a powerful tool for system identification. While prior work has focused on identifying robot properties using robot-specific data or object properties using object-specific data, our approach calibrates…

Model-free policy learning has enabled robust performance of complex tasks with relatively simple algorithms. However, this simplicity comes at the cost of requiring an Oracle and arguably very poor sample complexity. This renders such…

As the field of AI continues to evolve, a significant dimension of this progression is the development of Large Language Models and their potential to enhance multi-agent artificial intelligence systems. This paper explores the cooperative…

Efficient adaptation between Egocentric (Ego) and Exocentric (Exo) views is crucial for applications such as human-robot cooperation. However, the success of most existing Ego-Exo adaptation methods relies heavily on target-view data for…

Existing Vehicle-to-Everything (V2X) cooperative perception methods rely on accurate multi-agent 3D annotations. Nevertheless, it is time-consuming and expensive to collect and annotate real-world data, especially for V2X systems. In this…

This paper is concerned with evaluating different multiagent learning (MAL) algorithms in problems where individual agents may be heterogenous, in the sense of utilizing different learning strategies, without the opportunity for prior…

Developing agents that can follow multimodal instructions remains a fundamental challenge in robotics and AI. Although large-scale pre-training on unlabeled datasets (no language instruction) has enabled agents to learn diverse behaviors,…

Ad hoc teamwork refers to the problem of enabling an agent to collaborate with teammates without prior coordination. Data-driven methods represent the state of the art in ad hoc teamwork. They use a large labeled dataset of prior…