Related papers: Divide, Discover, Deploy: Factorized Skill Learnin…
Shared-autonomy imitation learning lets a human correct a robot in real time, mitigating covariate-shift errors. Yet existing approaches ignore two critical factors: (i) the operator's cognitive load and (ii) the risk created by delayed or…
Unsupervised landmarks discovery (ULD) for an object category is a challenging computer vision problem. In pursuit of developing a robust ULD framework, we explore the potential of a recent paradigm of self-supervised learning algorithms,…
Federated learning is an emerging distributed machine learning framework aiming at protecting data privacy. Data heterogeneity is one of the core challenges in federated learning, which could severely degrade the convergence rate and…
Exploration is crucial for enabling legged robots to learn agile locomotion behaviors that can overcome diverse obstacles. However, such exploration is inherently challenging, and we often rely on extensive reward engineering, expert…
We develop a metalearning approach for learning hierarchically structured policies, improving sample efficiency on unseen tasks through the use of shared primitives---policies that are executed for large numbers of timesteps. Specifically,…
Semi-Supervised Learning (SSL) and Unsupervised Domain Adaptation (UDA) enhance the model performance by exploiting information from labeled and unlabeled data. The clustering assumption has proven advantageous for learning with limited…
We develop Upside-Down Reinforcement Learning (UDRL), a method for learning to act using only supervised learning techniques. Unlike traditional algorithms, UDRL does not use reward prediction or search for an optimal policy. Instead, it…
Zero-shot learning methods typically assume that the new, unseen classes encountered during deployment come from the same distribution as the the classes in the training set. However, real-world scenarios often involve class distribution…
Learning automatically the structure of object categories remains an important open problem in computer vision. In this paper, we propose a novel unsupervised approach that can discover and learn landmarks in object categories, thus…
Learning diverse skills without hand-crafted reward functions could accelerate reinforcement learning in downstream tasks. However, existing skill discovery methods focus solely on maximizing the diversity of skills without considering…
Reward learning enables robots to learn adaptable behaviors from human input. Traditional methods model the reward as a linear function of hand-crafted features, but that requires specifying all the relevant features a priori, which is…
Unsupervised skill discovery in Reinforcement Learning aims to mimic humans' ability to autonomously discover diverse behaviors. However, existing methods are often unconstrained, making it difficult to find useful skills, especially in…
As a pivotal branch of machine learning, manifold learning uncovers the intrinsic low-dimensional structure within complex nonlinear manifolds in high-dimensional space for visualization, classification, clustering, and gaining key…
With the development of deep learning techniques, supervised learning has achieved performances surpassing those of humans. Researchers have designed numerous corresponding models for different data modalities, achieving excellent results…
Reinforcement learning algorithms are typically limited to learning a single solution for a specified task, even though diverse solutions often exist. Recent studies showed that learning a set of diverse solutions is beneficial because…
While reinforcement learning (RL) has the potential to enable robots to autonomously acquire a wide range of skills, in practice, RL usually requires manual, per-task engineering of reward functions, especially in real world settings where…
Safety comes first in many real-world applications involving autonomous agents. Despite a large number of reinforcement learning (RL) methods focusing on safety-critical tasks, there is still a lack of high-quality evaluation of those…
Domain randomization in reinforcement learning is an established technique for increasing the robustness of control policies trained in simulation. By randomizing environment properties during training, the learned policy can become robust…
Integrating robots in complex everyday environments requires a multitude of problems to be solved. One crucial feature among those is to equip robots with a mechanism for teaching them a new task in an easy and natural way. When teaching…
Human motion is highly diverse and dynamic, posing challenges for imitation learning algorithms that aim to generalize motor skills for controlling simulated characters. Previous methods typically rely on a universal full-body controller…