Related papers: PEAC: Unsupervised Pre-training for Cross-Embodime…
A mainstream type of current self-supervised learning methods pursues a general-purpose representation that can be well transferred to downstream tasks, typically by optimizing on a given pretext task such as instance discrimination. In…
Designing effective task sequences is crucial for curriculum reinforcement learning (CRL), where agents must gradually acquire skills by training on intermediate tasks. A key challenge in CRL is to identify tasks that promote exploration,…
We present an approach for encoding visual task relationships to improve model performance in an Unsupervised Domain Adaptation (UDA) setting. Semantic segmentation and monocular depth estimation are shown to be complementary tasks; in a…
Deep reinforcement learning (RL) can acquire complex behaviors from low-level inputs, such as images. However, real-world applications of such methods require generalizing to the vast variability of the real world. Deep networks are known…
Unsupervised learning visible-infrared person re-identification (USL-VI-ReID) aims to learn modality-invariant features from unlabeled cross-modality datasets and reduce the inter-modality gap. However, the existing methods lack…
Generalizing deep reinforcement learning agents to unseen environments remains a significant challenge. One promising solution is Unsupervised Environment Design (UED), a co-evolutionary framework in which a teacher adaptively generates…
In XR downlink transmission, energy-efficient power scheduling (EEPS) is essential for conserving power resource while delivering large data packets within hard-latency constraints. Traditional constrained reinforcement learning (CRL)…
Deep reinforcement learning (RL) provides powerful methods for training optimal sequential decision-making agents. As collecting real-world interactions can entail additional costs and safety risks, the common paradigm of sim2real conducts…
Continual learning is a process that involves training learning agents to sequentially master a stream of tasks or classes without revisiting past data. The challenge lies in leveraging previously acquired knowledge to learn new tasks…
In this paper we propose a strategy for semi-supervised image classification that leverages unsupervised representation learning and co-training. The strategy, that is called CURL from Co-trained Unsupervised Representation Learning,…
Reinforcement learning (RL) is a machine learning approach that trains agents to maximize cumulative rewards through interactions with environments. The integration of RL with deep learning has recently resulted in impressive achievements…
Generalizing local navigation policies across diverse robot morphologies is a critical challenge. Progress is often hindered by the need for costly and embodiment-specific data, the tight coupling of planning and control, and the…
We study the problem of cross-embodiment inverse reinforcement learning, where we wish to learn a reward function from video demonstrations in one or more embodiments and then transfer the learned reward to a different embodiment (e.g.,…
Automated driving at unsignalized intersections is challenging due to complex multi-vehicle interactions and the need to balance safety and efficiency. Model Predictive Control (MPC) offers structured constraint handling through…
Continuous-time nonlinear optimal control problems hold great promise in real-world applications. After decades of development, reinforcement learning (RL) has achieved some of the greatest successes as a general nonlinear control design…
Visual navigation is a task of training an embodied agent by intelligently navigating to a target object (e.g., television) using only visual observations. A key challenge for current deep reinforcement learning models lies in the…
A central goal of unsupervised learning is to acquire representations from unlabeled data or experience that can be used for more effective learning of downstream tasks from modest amounts of labeled data. Many prior unsupervised learning…
Model-based reinforcement learning (MBRL) and model-free reinforcement learning (MFRL) evolve along distinct paths but converge in the design of Dyna-Q [1]. However, modern RL methods still struggle with effective transferability across…
Model Predictive Control (MPC) provides interpretable, tunable locomotion controllers grounded in physical models, but its robustness depends on frequent replanning and is limited by model mismatch and real-time computational constraints.…
Reinforcement Learning (RL) algorithms are often known for sample inefficiency and difficult generalization. Recently, Unsupervised Environment Design (UED) emerged as a new paradigm for zero-shot generalization by simultaneously learning a…