相关论文: Zero-shot generalization using cascaded system-rep…

Reinforcement learning holds the promise of enabling autonomous robots to learn large repertoires of behavioral skills with minimal human intervention. However, robotic applications of reinforcement learning often compromise the autonomy of…

We introduce a differentiable framework for zero-shot adaptive control over parametric families of nonlinear dynamical systems. Our approach integrates a function encoder-based neural ODE (FE-NODE) for modeling system dynamics with a…

We improve zero-shot learning (ZSL) by incorporating common-sense knowledge in DNNs. We propose Common-Sense based Neuro-Symbolic Loss (CSNL) that formulates prior knowledge as novel neuro-symbolic loss functions that regularize…

Supervised learning (SL) and reinforcement learning (RL) are both widely used to train general-purpose agents for complex tasks, yet their generalization capabilities and underlying mechanisms are not yet fully understood. In this paper, we…

Behavioral cloning uses a dataset of demonstrations to learn a policy. To overcome computationally expensive training procedures and address the policy adaptation problem, we propose to use latent spaces of pre-trained foundation models to…

In this paper, a deep reinforcement learning based method is proposed to obtain optimal policies for optimal infinite-horizon control of probabilistic Boolean control networks (PBCNs). Compared with the existing literatures, the proposed…

Goal-conditioned policy learning for robotic manipulation presents significant challenges in maintaining performance across diverse objectives and environments. We introduce Hyper-GoalNet, a framework that generates task-specific policy…

Humans perceive the world through multiple senses, enabling them to create a comprehensive representation of their surroundings and to generalize information across domains. For instance, when a textual description of a scene is given,…

Training intelligent agents that can drive autonomously in various urban and highway scenarios has been a hot topic in the robotics society within the last decades. However, the diversity of driving environments in terms of road topology…

Deep reinforcement learning has enabled robots to learn motor skills from environmental interactions with minimal to no prior knowledge. However, existing reinforcement learning algorithms assume an episodic setting, in which the agent…

In this work, we present a novel meta-learning algorithm, i.e. TTNet, that regresses model parameters for novel tasks for which no ground truth is available (zero-shot tasks). In order to adapt to novel zero-shot tasks, our meta-learner…

Deep learning models exhibit limited generalizability across different domains. Specifically, transferring knowledge from available entangled domain features(source/target domain) and categorical features to new unseen categorical features…

How to learn an effective reinforcement learning-based model for control tasks from high-level visual observations is a practical and challenging problem. A key to solving this problem is to learn low-dimensional state representations from…

Most model-free reinforcement learning methods leverage state representations (embeddings) for generalization, but either ignore structure in the space of actions or assume the structure is provided a priori. We show how a policy can be…

Learned Neural Network based policies have shown promising results for robot navigation. However, most of these approaches fall short of being used on a real robot due to the extensive simulated training they require. These simulations lack…

To more efficiently address image compressed sensing (CS) problems, we present a novel content-aware scalable network dubbed CASNet which collectively achieves adaptive sampling rate allocation, fine granular scalability and high-quality…

We demonstrate the possibility of learning drone swarm controllers that are zero-shot transferable to real quadrotors via large-scale multi-agent end-to-end reinforcement learning. We train policies parameterized by neural networks that are…

While reinforcement learning methods have delivered remarkable results in a number of settings, generalization, i.e., the ability to produce policies that generalize in a reliable and systematic way, has remained a challenge. The problem of…

Diffusion-based robot navigation policies trained on large-scale imitation learning datasets, can generate multi-modal trajectories directly from the robot's visual observations, bypassing the traditional localization-mapping-planning…

Imitation learning enables intelligent systems to acquire complex behaviors with minimal supervision. However, existing methods often focus on short-horizon skills, require large datasets, and struggle to solve long-horizon tasks or…