Related papers: Cross-environment Cooperation Enables Zero-shot Mu…
Learning what to share between tasks has been a topic of great importance recently, as strategic sharing of knowledge has been shown to improve downstream task performance. This is particularly important for multilingual applications, as…
We use model-free reinforcement learning, extensive simulation, and transfer learning to develop a continuous control algorithm that has good zero-shot performance in a real physical environment. We train a simulated agent to act optimally…
In this work we create agents that can perform well beyond a single, individual task, that exhibit much wider generalisation of behaviour to a massive, rich space of challenges. We define a universe of tasks within an environment domain and…
Collective human knowledge has clearly benefited from the fact that innovations by individuals are taught to others through communication. Similar to human social groups, agents in distributed learning systems would likely benefit from…
The goal of object-centric representation learning is to decompose visual scenes into a structured representation that isolates the entities. Recent successes have shown that object-centric representation learning can be scaled to…
Almost all multi-agent reinforcement learning algorithms without communication follow the principle of centralized training with decentralized execution. During centralized training, agents can be guided by the same signals, such as the…
Learning collaborative behaviors is essential for multi-agent systems. Traditionally, multi-agent reinforcement learning solves this implicitly through a joint reward and centralized observations, assuming collaborative behavior will…
Zero-Shot Classification (ZSC) equips the learned model with the ability to recognize the visual instances from the novel classes via constructing the interactions between the visual and the semantic modalities. In contrast to the…
Single-agent reinforcement learning algorithms in a multi-agent environment are inadequate for fostering cooperation. If intelligent agents are to interact and work together to solve complex problems, methods that counter non-cooperative…
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…
Many challenges remain before AI agents can be deployed in real-world environments. However, one virtue of such environments is that they are inherently multi-agent and contain human experts. Using advanced social intelligence in such an…
Learning to collaborate has witnessed significant progress in multi-agent reinforcement learning (MARL). However, promoting coordination among agents and enhancing exploration capabilities remain challenges. In multi-agent environments,…
Recent works have proven that intricate cooperative behaviors can emerge in agents trained using meta reinforcement learning on open ended task distributions using self-play. While the results are impressive, we argue that self-play and…
The cooperation among AI systems, and between AI systems and humans is becoming increasingly important. In various real-world tasks, an agent needs to cooperate with unknown partner agent types. This requires the agent to assess the…
In many coordination problems, independently reasoning humans are able to discover mutually compatible policies. In contrast, independently trained self-play policies are often mutually incompatible. Zero-shot coordination (ZSC) has…
Collaborative multi-agent exploration of unknown environments is crucial for search and rescue operations. Effective real-world deployment must address challenges such as limited inter-agent communication and static and dynamic obstacles.…
We introduce the Overcooked Generalisation Challenge (OGC) - a new benchmark for evaluating reinforcement learning (RL) agents on their ability to cooperate with unknown partners in unfamiliar environments. Existing work typically evaluated…
Zero-shot coordination (ZSC) is a significant challenge in multi-agent collaboration, aiming to develop agents that can coordinate with unseen partners they have not encountered before. Recent cutting-edge ZSC methods have primarily focused…
Intelligent organisms can solve truly novel problems which they have never encountered before, either in their lifetime or their evolution. An important component of this capacity is the ability to ``think'', that is, to mentally manipulate…
Collective intelligence is a fundamental trait shared by several species of living organisms. It has allowed them to thrive in the diverse environmental conditions that exist on our planet. From simple organisations in an ant colony to…