相关论文: Zero-shot Policy Learning with Spatial Temporal Re…

We address the problem of reinforcement learning in which observations may exhibit an arbitrary form of stochastic dependence on past observations and actions, i.e. environments more general than (PO)MDPs. The task for an agent is to attain…

Unsupervised domain adaptation aims to transfer knowledge from a source domain to a target domain so that the target domain data can be recognized without any explicit labelling information for this domain. One limitation of the problem…

While deep reinforcement learning techniques have led to agents that are successfully able to learn to perform a number of tasks that had been previously unlearnable, these techniques are still susceptible to the longstanding problem of…

In the early stages of human life, babies develop their skills by exploring different scenarios motivated by their inherent satisfaction rather than by extrinsic rewards from the environment. This behavior, referred to as intrinsic…

Zero-shot recognition (ZSR) deals with the problem of predicting class labels for target domain instances based on source domain side information (e.g. attributes) of unseen classes. We formulate ZSR as a binary prediction problem. Our…

Legged robots have unparalleled mobility on unstructured terrains. However, it remains an open challenge to design locomotion controllers that can operate in a large variety of environments. In this paper, we address this challenge of…

When learning to behave in a stochastic environment where safety is critical, such as driving a vehicle in traffic, it is natural for human drivers to plan fallback strategies as a backup to use if ever there is an unexpected change in the…

Computer simulation provides an automatic and safe way for training robotic control policies to achieve complex tasks such as locomotion. However, a policy trained in simulation usually does not transfer directly to the real hardware due to…

Children can rapidly generalize compositionally-constructed rules to unseen test sets. On the other hand, deep reinforcement learning (RL) agents need to be trained over millions of episodes, and their ability to generalize to unseen…

We propose a novel robotic system that can improve its perception during deployment. Contrary to the established approach of learning semantics from large datasets and deploying fixed models, we propose a framework in which semantic models…

Navigating unfamiliar environments presents significant challenges for household robots, requiring the ability to recognize and reason about novel decoration and layout. Existing reinforcement learning methods cannot be directly transferred…

Existing Reinforcement Learning (RL) systems encounter significant challenges when applied to real-world scenarios, primarily due to poor generalization across environments that differ from their training conditions. This thesis explores…

In computational reinforcement learning, a growing body of work seeks to construct an agent's perception of the world through predictions of future sensations; predictions about environment observations are used as additional input features…

The interpretation of spatial references is highly contextual, requiring joint inference over both language and the environment. We consider the task of spatial reasoning in a simulated environment, where an agent can act and receive…

Cross-task generalization is a core challenge in open-world robotic manipulation, and the key lies in extracting transferable manipulation knowledge from seen tasks. Recent in-context learning approaches leverage seen task demonstrations to…

Object recognition systems usually require fully complete manually labeled training data to train the classifier. In this paper, we study the problem of object recognition where the training samples are missing during the classifier…

Dealing with sparse rewards is one of the biggest challenges in Reinforcement Learning (RL). We present a novel technique called Hindsight Experience Replay which allows sample-efficient learning from rewards which are sparse and binary and…

Recently, zero-shot learning (ZSL) emerged as an exciting topic and attracted a lot of attention. ZSL aims to classify unseen classes by transferring the knowledge from seen classes to unseen classes based on the class description. Despite…

In reinforcement learning (RL), sparse rewards are a natural way to specify the task to be learned. However, most RL algorithms struggle to learn in this setting since the learning signal is mostly zeros. In contrast, humans are good at…

Recent robot learning methods commonly rely on imitation learning from massive robotic dataset collected with teleoperation. When facing a new task, such methods generally require collecting a set of new teleoperation data and finetuning…