Related papers: Select before Act: Spatially Decoupled Action Repe…
Recent work has shown that reinforcement learning (RL) is a promising approach to control dynamical systems described by partial differential equations (PDE). This paper shows how to use RL to tackle more general PDE control problems that…
Reinforcement learning (RL) is rapidly reaching and surpassing human-level control capabilities. However, state-of-the-art RL algorithms often require timesteps and reaction times significantly faster than human capabilities, which is…
For many space applications, traditional control methods are often used during operation. However, as the number of space assets continues to grow, autonomous operation can enable rapid development of control methods for different space…
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…
Despite the central role of action in embodied intelligence, learning transferable action representations from visual transitions remains a fundamental challenge, particularly when world models must generalize across embodiments under…
Deep reinforcement learning (RL) algorithms can use high-capacity deep networks to learn directly from image observations. However, these high-dimensional observation spaces present a number of challenges in practice, since the policy must…
Skill-based reinforcement learning (RL) has emerged as a promising strategy to leverage prior knowledge for accelerated robot learning. Skills are typically extracted from expert demonstrations and are embedded into a latent space from…
Reinforcement Learning (RL) based methods have seen their paramount successes in solving serial decision-making and control problems in recent years. For conventional RL formulations, Markov Decision Process (MDP) and state-action-value…
Continual self-supervised learning (CSSL) methods have gained increasing attention in remote sensing (RS) due to their capability to learn new tasks sequentially from continuous streams of unlabeled data. Existing CSSL methods, while…
Current reinforcement learning (RL) methods can successfully learn single tasks but often generalize poorly to modest perturbations in task domain or training procedure. In this work, we present a decoupled learning strategy for RL that…
Reinforcement Learning (RL) is a computational approach to reward-driven learning in sequential decision problems. It implements the discovery of optimal actions by learning from an agent interacting with an environment rather than from…
Sampling is ubiquitous in machine learning methodologies. Due to the growth of large datasets and model complexity, we want to learn and adapt the sampling process while training a representation. Towards achieving this grand goal, a…
Offline policy improvement faces an inherent conflict between maximizing value and fitting the data distribution. While in-sample weighted regression is stable, it suffers from over-conservatism that suppresses high-value actions in the…
In this work, we first describe a framework for the application of Reinforcement Learning (RL) control to a radar system that operates in a congested spectral setting. We then compare the utility of several RL algorithms through a…
In this paper we consider self-supervised representation learning to improve sample efficiency in reinforcement learning (RL). We propose a forward prediction objective for simultaneously learning embeddings of states and action sequences.…
Deep reinforcement learning (DRL) frameworks are increasingly used to solve high-dimensional continuous control tasks in robotics. However, due to the lack of sample efficiency, applying DRL for online learning is still practically…
This paper focuses on the scalable robot learning for manipulation in the dexterous robot arm-hand systems, where the remote human-robot interactions via augmented reality (AR) are established to collect the expert demonstration data for…
Real-world sequential decision-making often involves parameterized action spaces that require both, decisions regarding discrete actions and decisions about continuous action parameters governing how an action is executed. Existing…
Planning-based reinforcement learning has shown strong performance in tasks in discrete and low-dimensional continuous action spaces. However, planning usually brings significant computational overhead for decision-making, and scaling such…
Ring attractors, mathematical models inspired by neural circuit dynamics, provide a biologically plausible mechanism to improve learning speed and accuracy in Reinforcement Learning (RL). Serving as specialized brain-inspired structures…