Related papers: Cross-environment Cooperation Enables Zero-shot Mu…

It is common to implicitly assume access to intelligently captured inputs (e.g., photos from a human photographer), yet autonomously capturing good observations is itself a major challenge. We address the problem of learning to look around:…

Exploration in decentralized cooperative multi-agent reinforcement learning faces two challenges. One is that the novelty of global states is unavailable, while the novelty of local observations is biased. The other is how agents can…

Cooperative multi-agent reinforcement learning often assumes a fixed execution team, yet many decentralized systems must operate with varying numbers of active agents during deployment. We study this setting under episodic roster variation:…

Zero-shot learning (ZSL) aims to recognize unseen objects using disjoint seen objects via sharing attributes. The generalization performance of ZSL is governed by the attributes, which transfer semantic information from seen classes to…

Imitation learning is effective for training agents when expert demonstrations are available, but collecting demonstrations for every complex task in an environment is costly. We study the long-horizon, goal-conditioned setting where a…

In multi-agent deep reinforcement learning (MADRL), agents can communicate with one another to perform a task in a coordinated manner. When multiple tasks are involved, agents can also leverage knowledge from one task to improve learning in…

Being able to cooperate with diverse humans is an important component of many economically valuable AI tasks, from household robotics to autonomous driving. However, generalizing to novel humans requires training on data that captures the…

Zero-shot learning (ZSL) aims to recognize objects of novel classes without any training samples of specific classes, which is achieved by exploiting the semantic information and auxiliary datasets. Recently most ZSL approaches focus on…

In this paper, we present a solution to a design problem of control strategies for multi-agent cooperative transport. Although existing learning-based methods assume that the number of agents is the same as that in the training environment,…

One-shot imitation is to learn a new task from a single demonstration, yet it is a challenging problem to adopt it for complex tasks with the high domain diversity inherent in a non-stationary environment. To tackle the problem, we explore…

As AI becomes more prevalent throughout society, effective methods of integrating humans and AI systems that leverage their respective strengths and mitigate risk have become an important priority. In this paper, we introduce the paradigm…

As humans, robots, and software agents increasingly share safety-critical environments, coordination must move from static task allocation to managing uncertain commitments. Existing frameworks fall short: they either assume rigid, static…

We present a framework for learning human user models from joint-action demonstrations that enables the robot to compute a robust policy for a collaborative task with a human. The learning takes place completely automatically, without any…

Zero-shot classification is a promising paradigm to solve an applicable problem when the training classes and test classes are disjoint. Achieving this usually needs experts to externalize their domain knowledge by manually specifying a…

Most of the existing artificial neural networks(ANNs) fail to learn continually due to catastrophic forgetting, while humans can do the same by maintaining previous tasks' performances. Although storing all the previous data can alleviate…

The field of Human-Robot Collaboration (HRC) has seen a considerable amount of progress in recent years. Thanks in part to advances in control and perception algorithms, robots have started to work in increasingly unstructured environments,…

Achieving cooperation among self-interested agents remains a fundamental challenge in multi-agent reinforcement learning. Recent work showed that mutual cooperation can be induced between "learning-aware" agents that account for and shape…

This paper considers the problem of learning a control policy for robot motion planning with zero-shot generalization, i.e., no data collection and policy adaptation is needed when the learned policy is deployed in new environments. We…

It is widely known how the human ability to cooperate has influenced the thriving of our species. However, as we move towards a hybrid human-machine future, it is still unclear how the introduction of AI agents in our social interactions…

One of the key challenges for multi-agent learning is scalability. In this paper, we introduce a technique for speeding up multi-agent learning by exploiting concurrent and incremental experience sharing. This solution adaptively identifies…