Related papers: Shaping Zero-Shot Coordination via State Blocking

Simulation based learning often provides a cost-efficient recourse to reinforcement learning applications in robotics. However, simulators are generally incapable of accurately replicating real-world dynamics, and thus bridging the sim2real…

Zero-Shot learning has been shown to be an efficient strategy for domain adaptation. In this context, this paper builds on the recent work of Bucher et al. [1], which proposed an approach to solve Zero-Shot classification problems (ZSC) by…

While goal-conditioned behavior cloning (GCBC) methods can perform well on in-distribution training tasks, they do not necessarily generalize zero-shot to tasks that require conditioning on novel state-goal pairs, i.e. combinatorial…

Large language models (LLMs) have shown increasing capacity at planning and executing a high-level goal in a live computer environment (e.g. MiniWoB++). To perform a task, recent works often require a model to learn from trace examples of…

Zero-shot transfer learning for Dialogue State Tracking (DST) helps to handle a variety of task-oriented dialogue domains without the cost of collecting in-domain data. Existing works mainly study common data- or model-level augmentation…

Semantic encoders and decoders for digital semantic communication (SC) often struggle to adapt to variations in unpredictable channel environments and diverse system designs. To address these challenges, this paper proposes a novel…

In image recognition, there are many cases where training samples cannot cover all target classes. Zero-shot learning (ZSL) utilizes the class semantic information to classify samples of the unseen categories that have no corresponding…

This paper proposes the Cooperative Soft Actor Critic (CSAC) method of enabling consecutive reinforcement learning agents to cooperatively solve a long time horizon multi-stage task. This method is achieved by modifying the policy of each…

This paper presents a scalable Bayesian technique for decentralized state estimation from multiple platforms in dynamic environments. As has long been recognized, centralized architectures impose severe scaling limitations for distributed…

This paper aims to solve the coordination of a team of robots traversing a route in the presence of adversaries with random positions. Our goal is to minimize the overall cost of the team, which is determined by (i) the accumulated risk…

Creating scalable and believable game societies requires balancing authorial control with computational cost. Existing scripted NPC systems scale efficiently but are often rigid, whereas fully LLM-driven agents can produce richer social…

RoboCup represents an International testbed for advancing research in AI and robotics, focusing on a definite goal: developing a robot team that can win against the human world soccer champion team by the year 2050. To achieve this goal,…

Agents in dynamic multi-agent environments must monitor their peers to execute individual and group plans. A key open question is how much monitoring of other agents' states is required to be effective: The Monitoring Selectivity Problem.…

When deployed in the real world, AI agents will inevitably face challenges that exceed their individual capabilities. A critical component of AI safety is an agent's ability to recognize when it is likely to fail in a novel situation and to…

Learning accurate models of the physical world is required for a lot of robotic manipulation tasks. However, during manipulation, robots are expected to interact with unknown workpieces so that building predictive models which can…

In large groups, every collaborative act requires balancing two pressures: the need to achieve behavioural synchrony and the need to keep free riding to a minimum. This paper introduces a model of collaboration that requires both…

Business process collaboration between independent parties can be challenging, especially if the participants do not have complete trust in each other. Tracking actions and enforcing the activity authorizations of participants via…

Flocking behavior has attracted considerable attention in multi-agent systems. The structure of flocking has been predominantly studied through the application of artificial potential fields coupled with velocity consensus. These…

Zero-Shot Learning (ZSL) is an emerging research that aims to solve the classification problems with very few training data. The present works on ZSL mainly focus on the mapping of learning semantic space to visual space. It encounters many…

A key challenge in multi-robot and multi-agent systems is generating solutions that are robust to other self-interested or even adversarial parties who actively try to prevent the agents from achieving their goals. The practicality of…