Related papers: COBRA: Data-Efficient Model-Based RL through Unsup…

Exploration is a difficult challenge in reinforcement learning and even recent state-of-the art curiosity-based methods rely on the simple epsilon-greedy strategy to generate novelty. We argue that pure random walks do not succeed to…

We present a reinforcement learning (RL) framework for controlling particle accelerator experiments that builds explainable physics-based constraints on agent behavior. The goal is to increase transparency and trust by letting users verify…

The integration of unmanned platforms equipped with advanced sensors promises to enhance situational awareness and mitigate the "fog of war" in military operations. However, managing the vast influx of data from these platforms poses a…

A compact information-rich representation of the environment, also called a feature abstraction, can simplify a robot's task of mapping its raw sensory inputs to useful action sequences. However, in environments that are non-stationary and…

Interactive search can provide a better experience by incorporating interaction feedback from the users. This can significantly improve search accuracy as it helps avoid irrelevant information and captures the users' search intents.…

Deep reinforcement learning (DRL) is one of the most powerful tools for synthesizing complex robotic behaviors. But training DRL models is incredibly compute and memory intensive, requiring large training datasets and replay buffers to…

The use of mobile robots is being popular over the world mainly for autonomous explorations in hazardous/ toxic or unknown environments. This exploration will be more effective and efficient if the explorations in unknown environment can be…

In this paper we present our scientific discovery that good representation can be learned via continuous attention during the interaction between Unsupervised Learning(UL) and Reinforcement Learning(RL) modules driven by intrinsic…

Reinforcement Learning enables to train an agent via interaction with the environment. However, in the majority of real-world scenarios, the extrinsic feedback is sparse or not sufficient, thus intrinsic reward formulations are needed to…

Physical construction---the ability to compose objects, subject to physical dynamics, to serve some function---is fundamental to human intelligence. We introduce a suite of challenging physical construction tasks inspired by how children…

Identifying uncertainty and taking mitigating actions is crucial for safe and trustworthy reinforcement learning agents, especially when deployed in high-risk environments. In this paper, risk sensitivity is promoted in a model-based…

Model-free deep-reinforcement-based learning algorithms have been applied to a range of COPs~\cite{bello2016neural}~\cite{kool2018attention}~\cite{nazari2018reinforcement}. However, these approaches suffer from two key challenges when…

In many contemporary applications such as healthcare, finance, robotics, and recommendation systems, continuous deployment of new policies for data collection and online learning is either cost ineffective or impractical. We consider a…

We present a new model-based algorithm for reinforcement learning (RL) which consists of explicit exploration and exploitation phases, and is applicable in large or infinite state spaces. The algorithm maintains a set of dynamics models…

We study how representation learning can accelerate reinforcement learning from rich observations, such as images, without relying either on domain knowledge or pixel-reconstruction. Our goal is to learn representations that both provide…

This paper presents a novel approach to modeling curiosity in a mobile robot, which is useful for monitoring and adaptive data collection tasks, especially in the context of long term autonomous missions where pre-programmed missions are…

We investigate robust model-free reinforcement learning algorithms designed for environments that may be dynamic or even adversarial. Traditional state-based policies often struggle to accommodate the challenges imposed by the presence of…

The most data-efficient algorithms for reinforcement learning (RL) in robotics are based on uncertain dynamical models: after each episode, they first learn a dynamical model of the robot, then they use an optimization algorithm to find a…

Efficient exploration remains a challenging research problem in reinforcement learning, especially when an environment contains large state spaces, deceptive local optima, or sparse rewards. To tackle this problem, we present a…

Preference-based reinforcement learning (PbRL) can enable robots to learn to perform tasks based on an individual's preferences without requiring a hand-crafted reward function. However, existing approaches either assume access to a…