Related papers: Mind the Sim-to-Real Gap & Think Like a Scientist

To address the computational challenges of Model Predictive Control (MPC), recent research has studied using imitation learning to approximate MPC with a computationally efficient Deep Neural Network (DNN). However, this introduces a common…

In computer experiments, a mathematical model implemented on a computer is used to represent complex physical phenomena. These models, known as computer simulators, enable experimental study of a virtual representation of the complex…

Recently, a framework for application-oriented optimal experiment design has been introduced. In this context, the distance of the estimated system from the true one is measured in terms of a particular end-performance metric. This…

Dynamic, risk-based pricing can systematically exclude vulnerable consumer groups from essential resources such as health insurance and consumer credit. We show that a regulator can realign private incentives with social objectives through…

In reinforcement learning, an agent interacts sequentially with an environment to maximize a reward, receiving only partial, probabilistic feedback. This creates a fundamental exploration-exploitation trade-off: the agent must explore to…

Simulation-based testing of autonomous vehicles (AVs) has become an essential complement to road testing to ensure safety. Consequently, substantial research has focused on searching for failure scenarios in simulation. However, a…

An emulator is a fast-to-evaluate statistical approximation of a detailed mathematical model (simulator). When used in lieu of simulators, emulators can expedite tasks that require many repeated evaluations, such as sensitivity analyses,…

Simulation agents are essential for designing and testing systems that interact with humans, such as autonomous vehicles (AVs). These agents serve various purposes, from benchmarking AV performance to stress-testing system limits, but all…

Manipulation in clutter requires solving complex sequential decision making problems in an environment rich with physical interactions. The transfer of motion planning solutions from simulation to the real world, in open-loop, suffers from…

In complex systems, many different parts interact in non-obvious ways. Traditional research focuses on a few or a single aspect of the problem so as to analyze it with the tools available. To get a better insight of phenomena that emerge…

The quintessential model-based reinforcement-learning agent iteratively refines its estimates or prior beliefs about the true underlying model of the environment. Recent empirical successes in model-based reinforcement learning with…

Reinforcement learning (RL) is playing an increasingly important role in fields such as robotic control and autonomous driving. However, the gap between simulation and the real environment remains a major obstacle to the practical…

Agent-based simulation with a synthetic population can help us compare different treatment conditions while keeping everything else constant within the same population (i.e., as digital twins). Such population-scale simulations require…

Reinforcement learning often requires extensive training data. Simulation-to-real transfer offers a promising approach to address this challenge in robotics. While differentiable simulators offer improved sample efficiency through exact…

For a robot to learn a good policy, it often requires expensive equipment (such as sophisticated sensors) and a prepared training environment conducive to learning. However, it is seldom possible to perfectly equip robots for economic…

Automated Vehicles require exhaustive testing in simulation to detect as many safety-critical failures as possible before deployment on public roads. In this work, we focus on the core decision-making component of autonomous robots: their…

Humans routinely rely on memory to perform tasks, yet most robot policies lack this capability; our goal is to endow robot policies with the same ability. Naively conditioning on long observation histories is computationally expensive and…

A fundamental challenge in science and engineering is the simulation-to-experiment gap. While we often possess prior knowledge of physical laws, these physical laws can be too difficult to solve exactly for complex systems. Such systems are…

In nested simulation literature, a common assumption is that the experimenter can choose the number of outer scenarios to sample. This paper considers the case when the experimenter is given a fixed set of outer scenarios from an external…

We study the problem of programmatic reinforcement learning, in which policies are represented as short programs in a symbolic language. Programmatic policies can be more interpretable, generalizable, and amenable to formal verification…