Related papers: Herd's Eye View: Improving Game AI Agent Learning …
The LiDAR-based multi-agent and single-agent perception has shown promising performance in environmental understanding for robots and automated vehicles. However, there is no existing method that simultaneously solves both multi-agent and…
Decentralized combinatorial optimization in evolving multi-agent systems poses significant challenges, requiring agents to balance long-term decision-making, short-term optimized collective outcomes, while preserving autonomy of interactive…
In order to engage in complex social interaction, humans learn at a young age to infer what others see and cannot see from a different point-of-view, and learn to predict others' plans and behaviors. These abilities have been mostly lacking…
Human-object interaction (HOI) detection aims to localize human-object pairs and the interactions between them. Existing methods operate under a closed-world assumption, treating the task as a classification problem over a small, predefined…
When humans work together to complete a joint task, each person builds an internal model of the situation and how it will evolve. Efficient collaboration is dependent on how these individual models overlap to form a shared mental model…
Video understanding is fundamental to tasks such as action recognition, video reasoning, and robotic control. Early video understanding methods based on large vision-language models (LVLMs) typically adopt a single-pass reasoning paradigm…
Experience replay is an important technique for addressing sample-inefficiency in deep reinforcement learning (RL), but faces difficulty in learning from binary and sparse rewards due to disproportionately few successful experiences in the…
In multi-vehicle cooperative driving tasks involving high-frequency continuous control, traditional state-based reward functions suffer from the issue of vanishing reward differences. This phenomenon results in a low signal-to-noise ratio…
We present a machine learning framework for multi-agent systems to learn both the optimal policy for maximizing the rewards and the encoding of the high dimensional visual observation. The encoding is useful for sharing local visual…
Connected and automated vehicles (CAVs) have attracted more and more attention recently. The fast actuation time allows them having the potential to promote the efficiency and safety of the whole transportation system. Due to technical…
Long-form video understanding remains fundamentally challenged by pervasive spatiotemporal redundancy and intricate narrative dependencies that span extended temporal horizons. While recent structured representations compress visual…
AI agents deployed in assistive roles often have to collaborate with other agents (humans, AI systems) without prior coordination. Methods considered state of the art for such ad hoc teamwork often pursue a data-driven approach that needs a…
Collaborative perception aims to extend sensing coverage and improve perception accuracy by sharing information among multiple agents. However, due to differences in viewpoints and spatial positions, agents often acquire heterogeneous…
Video prediction models combined with planning algorithms have shown promise in enabling robots to learn to perform many vision-based tasks through only self-supervision, reaching novel goals in cluttered scenes with unseen objects.…
Coordinating multiple embodied agents in dynamic environments remains a core challenge in artificial intelligence, requiring both perception-driven reasoning and scalable cooperation strategies. While recent works have leveraged large…
Long video understanding presents significant challenges for vision-language models due to extremely long context windows. Existing solutions relying on naive chunking strategies with retrieval-augmented generation, typically suffer from…
We introduce Heterogeneous Agent Collaborative Reinforcement Learning (HACRL), a new Reinforcement Learning from Verifiable Reward (RLVR) problem that addresses the inefficiencies of isolated multi-agent on-policy optimization. HACRL…
Reinforcement learning (RL) has produced spectacular results in games, robotics, and continuous control. Yet, despite these successes, learned policies often fail to generalize beyond their training distribution, limiting real-world impact.…
Multi-agent reinforcement learning (MARL) faces two critical bottlenecks distinct from single-agent RL: credit assignment in cooperative tasks and partial observability of environmental states. We propose LERO, a framework integrating Large…
Making sophisticated, robust, and safe sequential decisions is at the heart of intelligent systems. This is especially critical for planning in complex multi-agent environments, where agents need to anticipate other agents' intentions and…