Related papers: Imitation Learning Inputting Image Feature to Each…
Human learning relies on specialization -- distinct cognitive mechanisms working together to enable rapid learning. In contrast, most modern neural networks rely on a single mechanism: gradient descent over an objective function. This…
Majority of the modern meta-learning methods for few-shot classification tasks operate in two phases: a meta-training phase where the meta-learner learns a generic representation by solving multiple few-shot tasks sampled from a large…
We consider the problem of third-person imitation learning with the additional challenge that the learner must select the perspective from which they observe the expert. In our setting, each perspective provides only limited information…
Model-based reinforcement learning (MBRL) aims to learn a dynamic model to reduce the number of interactions with real-world environments. However, due to estimation error, rollouts in the learned model, especially those of long horizons,…
Current end-to-end deep Reinforcement Learning (RL) approaches require jointly learning perception, decision-making and low-level control from very sparse reward signals and high-dimensional inputs, with little capability of incorporating…
We present a deep imitation learning framework for robotic bimanual manipulation in a continuous state-action space. A core challenge is to generalize the manipulation skills to objects in different locations. We hypothesize that modeling…
Imitation can be viewed as a means of enhancing learning in multiagent environments. It augments an agent's ability to learn useful behaviors by making intelligent use of the knowledge implicit in behaviors demonstrated by cooperative…
Recent advances in one-shot imitation learning have enabled robots to acquire new manipulation skills from a single human demonstration. While existing methods achieve strong performance on single-step tasks, they remain limited in their…
Human perception is structured around objects which form the basis for our higher-level cognition and impressive systematic generalization abilities. Yet most work on representation learning focuses on feature learning without even…
Meta-learning enables algorithms to quickly learn a newly encountered task with just a few labeled examples by transferring previously learned knowledge. However, the bottleneck of current meta-learning algorithms is the requirement of a…
This paper presents an attempt to replicate the robot imitation work conducted by Sermanet et al., with a specific focus on the experiments involving robot joint position prediction. While the original study utilized human poses to predict…
Deep learning has been widely accepted as a promising solution for medical image segmentation, given a sufficiently large representative dataset of images with corresponding annotations. With ever increasing amounts of annotated medical…
Imitation learning in robots, also called programing by demonstration, has made important advances in recent years, allowing humans to teach context dependant motor skills/tasks to robots. We propose to extend the usual contexts…
In most applications of utilizing neural networks for mathematical optimization, a dedicated model is trained for each specific optimization objective. However, in many scenarios, several distinct yet correlated objectives or tasks often…
Modeling and prediction of human motion dynamics has long been a challenging problem in computer vision, and most existing methods rely on the end-to-end supervised training of various architectures of recurrent neural networks. Inspired by…
Continual learning in online scenario aims to learn a sequence of new tasks from data stream using each data only once for training, which is more realistic than in offline mode assuming data from new task are all available. However, this…
Despite the growing variety of languages supported by existing multilingual neural machine translation (MNMT) models, most of the world's languages are still being left behind. We aim to extend large-scale MNMT models to incorporate a new…
Continual learning of deep neural networks is a key requirement for scaling them up to more complex applicative scenarios and for achieving real lifelong learning of these architectures. Previous approaches to the problem have considered…
Imitation learning from large multi-task demonstration datasets has emerged as a promising path for building generally-capable robots. As a result, 1000s of hours have been spent on building such large-scale datasets around the globe.…
Imitation learning enables autonomous agents to learn from human examples, without the need for a reward signal. Still, if the provided dataset does not encapsulate the task correctly, or when the task is too complex to be modeled, such…