Related papers: Learning Continuous Control Policies for Informati…

In this paper, we describe a novel approach to imitation learning that infers latent policies directly from state observations. We introduce a method that characterizes the causal effects of latent actions on observations while…

This paper considers the problem of task-dependent (top-down) attention allocation for vision-based autonomous navigation using known landmarks. Unlike the existing paradigm in which landmark selection is formulated as a combinatorial…

A learning method is proposed for Koopman operator-based models with the goal of improving closed-loop control behavior. A neural network-based approach is used to discover a space of observables in which nonlinear dynamics is linearly…

We study continuous action reinforcement learning problems in which it is crucial that the agent interacts with the environment only through safe policies, i.e.,~policies that do not take the agent to undesirable situations. We formulate…

Autonomous systems are often required to operate in partially observable environments. They must reliably execute a specified objective even with incomplete information about the state of the environment. We propose a methodology to…

We study model-based learning of finite-window policies in tabular partially observable Markov decision processes (POMDPs). A common approach to learning under partial observability is to approximate unbounded history dependencies using…

Active learning identifies data points to label that are expected to be the most useful in improving a supervised model. Opportunistic active learning incorporates active learning into interactive tasks that constrain possible queries…

Many applications -- including power systems, robotics, and economics -- involve a dynamical system interacting with a stochastic and hard-to-model environment. We adopt a reinforcement learning approach to control such systems.…

In this paper, we study the design of an optimal transmission policy for remote state estimation over packet-dropping wireless channels with imperfect channel state information. A smart sensor uses a Kalman filter to estimate the system…

Robotic manipulation tasks often rely on static cameras for perception, which can limit flexibility, particularly in scenarios like robotic surgery and cluttered environments where mounting static cameras is impractical. Ideally, robots…

The control of a robot for manipulation tasks generally relies on object detection and pose estimation. An attractive alternative is to learn control policies directly from raw input data. However, this approach is time-consuming and…

In offline reinforcement learning, a policy is learned using a static dataset in the absence of costly feedback from the environment. In contrast to the online setting, only using static datasets poses additional challenges, such as…

We consider a control problem for a finite-state Markov system whose performance is evaluated by a coherent Markov risk measure. For each policy, the risk of a state is approximated by a function of its features, thus leading to a…

Making optimal decisions under uncertainty is a shared problem among distinct fields. While optimal control is commonly studied in the framework of dynamic programming, it is approached with differing perspectives of the Bellman optimality…

Given a Markov decision process (MDP), we seek to learn representations for a range of policies to facilitate behavior steering at test time. As policies of an MDP are uniquely determined by their occupancy measures, we propose modeling…

This paper presents a reinforcement learning approach to synthesizing task-driven control policies for robotic systems equipped with rich sensory modalities (e.g., vision or depth). Standard reinforcement learning algorithms typically…

We study the problem of learning exploration-exploitation strategies that effectively adapt to dynamic environments, where the task may change over time. While RNN-based policies could in principle represent such strategies, in practice…

We present a data-efficient reinforcement learning algorithm resistant to observation noise. Our method extends the highly data-efficient PILCO algorithm (Deisenroth & Rasmussen, 2011) into partially observed Markov decision processes…

We present a novel POMDP problem formulation for a robot that must autonomously decide where to go to collect new and scientifically relevant images given a limited ability to communicate with its human operator. From this formulation we…

The paper presents a complete pipeline for learning continuous motion control policies for a mobile robot when only a non-differentiable physics simulator of robot-terrain interactions is available. The multi-modal state estimation of the…