Related papers: Playful Interactions for Representation Learning

Most existing imitation learning approaches assume the demonstrations are drawn from experts who are optimal, but relaxing this assumption enables us to use a wider range of data. Standard imitation learning may learn a suboptimal policy…

Enabling autonomous robots to interact in unstructured environments with dynamic objects requires manipulation capabilities that can deal with clutter, changes, and objects' variability. This paper presents a comparison of different…

Imitation learning often needs a large demonstration set in order to handle the full range of situations that an agent might find itself in during deployment. However, collecting expert demonstrations can be expensive. Recent work in…

Tactile information is a critical tool for dexterous manipulation. As humans, we rely heavily on tactile information to understand objects in our environments and how to interact with them. We use touch not only to perform manipulation…

Tool use is essential for enabling robots to perform complex real-world tasks, but learning such skills requires extensive datasets. While teleoperation is widely used, it is slow, delay-sensitive, and poorly suited for dynamic tasks. In…

Autonomous learning of object manipulation skills can enable robots to acquire rich behavioral repertoires that scale to the variety of objects found in the real world. However, current motion skill learning methods typically restrict the…

We study self-supervised video representation learning, which is a challenging task due to 1) lack of labels for explicit supervision; 2) unstructured and noisy visual information. Existing methods mainly use contrastive loss with video…

In many sequential decision-making problems (e.g., robotics control, game playing, sequential prediction), human or expert data is available containing useful information about the task. However, imitation learning (IL) from a small amount…

One of the great promises of robot learning systems is that they will be able to learn from their mistakes and continuously adapt to ever-changing environments. Despite this potential, most of the robot learning systems today are deployed…

Modern vision models excel at general purpose downstream tasks. It is unclear, however, how they may be used for personalized vision tasks, which are both fine-grained and data-scarce. Recent works have successfully applied synthetic data…

Imitation learning trains a policy by mimicking expert demonstrations. Various imitation methods were proposed and empirically evaluated, meanwhile, their theoretical understanding needs further studies. In this paper, we firstly analyze…

Exploration is an extremely challenging problem in reinforcement learning, especially in high dimensional state and action spaces and when only sparse rewards are available. Effective representations can indicate which components of the…

Imitation learning enables robots to learn and replicate human behavior from training data. Recent advances in machine learning enable end-to-end learning approaches that directly process high-dimensional observation data, such as images.…

Practical Imitation Learning (IL) systems rely on large human demonstration datasets for successful policy learning. However, challenges lie in maintaining the quality of collected data and addressing the suboptimal nature of some…

Visual navigation tasks in real-world environments often require both self-motion and place recognition feedback. While deep reinforcement learning has shown success in solving these perception and decision-making problems in an end-to-end…

Humans can quickly learn new behaviors by leveraging background world knowledge. In contrast, agents trained with reinforcement learning (RL) typically learn behaviors from scratch. We thus propose a novel approach that uses the vast…

Robots often face situations where grasping a goal object is desirable but not feasible due to other present objects preventing the grasp action. We present a deep Reinforcement Learning approach to learn grasping and pushing policies for…

We consider the problem of building a state representation model in a continual fashion. As the environment changes, the aim is to efficiently compress the sensory state's information without losing past knowledge. The learned features are…

Robots could learn their own state and world representation from perception and experience without supervision. This desirable goal is the main focus of our field of interest, state representation learning (SRL). Indeed, a compact…

How to accurately learn task-relevant state representations from high-dimensional observations with visual distractions is a realistic and challenging problem in visual reinforcement learning. Recently, unsupervised representation learning…