Ensemble quantile networks: Uncertainty-aware reinforcement learning with applications in autonomous driving
Reinforcement learning (RL) can be used to create a decision-making agent for autonomous
driving. However, previous approaches provide black-box solutions, which do not offer …
driving. However, previous approaches provide black-box solutions, which do not offer …
Risk-averse model uncertainty for distributionally robust safe reinforcement learning
J Queeney, M Benosman - Advances in Neural Information …, 2024 - proceedings.neurips.cc
Many real-world domains require safe decision making in uncertain environments. In this
work, we introduce a deep reinforcement learning framework for approaching this important …
work, we introduce a deep reinforcement learning framework for approaching this important …
Safe control for nonlinear systems with stochastic uncertainty via risk control barrier functions
A Singletary, M Ahmadi… - IEEE Control Systems …, 2022 - ieeexplore.ieee.org
Guaranteeing safety for robotic and autonomous systems in real-world environments is a
challenging task that requires the mitigation of stochastic uncertainties. Control barrier …
challenging task that requires the mitigation of stochastic uncertainties. Control barrier …
Multi-robot coordination and planning in uncertain and adversarial environments
Abstract Purpose of Review Deploying a team of robots that can carefully coordinate their
actions can make the entire system robust to individual failures. In this report, we review …
actions can make the entire system robust to individual failures. In this report, we review …
Risk-aware motion planning in partially known environments
Recent trends envisage robots being deployed in areas deemed dangerous to humans,
such as buildings with gas and radiation leaks. In such situations, the model of the …
such as buildings with gas and radiation leaks. In such situations, the model of the …
Constrained risk-averse Markov decision processes
We consider the problem of designing policies for Markov decision processes (MDPs) with
dynamic coherent risk objectives and constraints. We begin by formulating the problem in a …
dynamic coherent risk objectives and constraints. We begin by formulating the problem in a …
Mean-variance policy iteration for risk-averse reinforcement learning
We present a mean-variance policy iteration (MVPI) framework for risk-averse control in a
discounted infinite horizon MDP optimizing the variance of a per-step reward random …
discounted infinite horizon MDP optimizing the variance of a per-step reward random …
Risk-sensitive motion planning using entropic value-at-risk
We consider the problem of risk-sensitive motion planning in the presence of randomly
moving obstacles. To this end, we adopt a model predictive control (MPC) scheme and pose …
moving obstacles. To this end, we adopt a model predictive control (MPC) scheme and pose …
Robust task scheduling for heterogeneous robot teams under capability uncertainty
This article develops a stochastic programming framework for multiagent systems, where
task decomposition, assignment, and scheduling problems are simultaneously optimized …
task decomposition, assignment, and scheduling problems are simultaneously optimized …
Temporal robustness of stochastic signals
We study the temporal robustness of stochastic signals. This topic is of particular interest in
interleaving processes such as multi-agent systems where communication and individual …
interleaving processes such as multi-agent systems where communication and individual …