Risk-averse autonomous systems: a brief history and recent developments from the perspective of optimal control
From MaRDI portal
Publication:2082497
DOI10.1016/j.artint.2022.103743OpenAlexW3201403052WikidataQ114206164 ScholiaQ114206164MaRDI QIDQ2082497
Margaret P. Chapman, Yuheng Wang
Publication date: 4 October 2022
Published in: Artificial Intelligence (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/2109.08947
Related Items (1)
Uses Software
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Time-inconsistent multistage stochastic programs: martingale bounds
- A theory of Markovian time-inconsistent stochastic control in discrete time
- Risk-averse dynamic programming for Markov decision processes
- Verification of discrete time stochastic hybrid systems: a stochastic reach-avoid decision problem
- Safe autonomy under perception uncertainty using chance-constrained temporal logic
- State-space formulae for all stabilizing controllers that satisfy an \(H_{\infty}\)-norm bound and relations to risk sensitivity
- Nash equilibria of risk-sensitive nonlinear stochastic differential games
- Risk-sensitive and minimax control of discrete-time, finite-state Markov decision processes
- An efficient off-line formulation of robust model predictive control using linear matrix inequalities
- Risk-sensitive reinforcement learning
- Data-driven robust optimization
- Data-driven distributionally robust optimization using the Wasserstein metric: performance guarantees and tractable reformulations
- A dynamic game approach to distributionally robust safety specifications for stochastic systems
- Set invariance in control
- Risk sensitive control of finite state Markov chains in discrete time, with applications to portfolio management
- \({\mathcal Q}\)-learning
- Minimax and risk averse multistage stochastic programming
- Markov decision processes with average-value-at-risk criteria
- Importance sampling in reinforcement learning with an estimated behavior policy
- Discounted approximations in risk-sensitive average Markov cost chains with finite state space
- A survey of inverse reinforcement learning: challenges, methods and progress
- Minimizing spectral risk measures applied to Markov decision processes
- Markov decision processes with recursive risk measures
- Erratum to ``Risk-averse dynamic programming for Markov decision processes
- Risk-sensitive mean field games via the stochastic maximum principle
- The scenario approach for stochastic model predictive control with bounds on closed-loop constraint violations
- Probabilistic reachability and safety for controlled discrete time stochastic hybrid systems
- Average optimality for risk-sensitive control with general state space
- On the minimax reachability of target sets and target tubes
- A stochastic games framework for verification and control of discrete time stochastic hybrid systems
- Coherent Measures of Risk
- Time-Consistent Decisions and Temporal Decomposition of Coherent Risk Functionals
- Risk-Sensitive Markov Control Processes
- Distributionally Robust Control of Constrained Stochastic Systems
- Risk-Constrained Markov Decision Processes
- Reach-avoid problems with time-varying dynamics, targets and constraints
- Stochastic Model Checking
- Discounted Approximations for Risk-Sensitive Average Criteria in Markov Decision Chains with Finite State Space
- Approximate Markov-Nash Equilibria for Discrete-Time Risk-Sensitive Mean-Field Games
- SAT Modulo ODE: A Direct SAT Approach to Hybrid Systems
- Lectures on Stochastic Programming
- Risk-sensitive linear/quadratic/gaussian control
- A risk-sensitive maximum principle: the case of imperfect state observation
- An adaptive optimal controller for discrete-time Markov environments
- Decision Problems with Expected Utility Criteria, II: Stationarity
- A note on a new class of recursive utilities in Markov decision processes
- 10.1162/jmlr.2003.3.4-5.803
- Optimization of stochastic linear systems with additive measurement and process noise using exponential performance criteria
- Safe Exploration of State and Action Spaces in Reinforcement Learning
- dReal: An SMT Solver for Nonlinear Theories over the Reals
- Risk-Sensitive Control of Discrete-Time Markov Processes with Infinite Horizon
- Wasserstein Distributionally Robust Stochastic Control: A Data-Driven Approach
- Stochastic Approximation for Risk-Aware Markov Decision Processes
- Formal Methods for Control of Traffic Flow: Automated Control Synthesis from Finite-State Transition Models
- More Risk-Sensitive Markov Decision Processes
- Optimal stochastic linear systems with exponential performance criteria and their relation to deterministic differential games
- A Framework for Time-Consistent, Risk-Sensitive Model Predictive Control: Theory and Algorithms
- Shrinking Horizon Model Predictive Control With Signal Temporal Logic Constraints Under Stochastic Disturbances
- Reachability analysis for neural feedback systems using regressive polynomial rule inference
- Verisig
- A Convex Analytic Approach to Risk-Aware Markov Decision Processes
- A time-dependent Hamilton-Jacobi formulation of reachable sets for continuous dynamic games
- Linear Quadratic Risk-Sensitive and Robust Mean Field Games
- Optimal Control of Conditional Value-at-Risk in Continuous Time
- Hamilton–Jacobi Formulation for Reach–Avoid Differential Games
- DSOS and SDSOS Optimization: More Tractable Alternatives to Sum of Squares and Semidefinite Optimization
- Risk-Sensitive Reinforcement Learning
- Infinite Horizon Risk Sensitive Control of Discrete Time Markov Processes under Minorization Property
- Risk-Sensitive Markov Decision Processes
- Q-Learning for Risk-Sensitive Control
- A Variational Formula for Risk-Sensitive Reward
- Exposition of a New Theory on the Measurement of Risk
- \(H^ \infty\)-optimal control and related minimax design problems. A dynamic game approach.
This page was built for publication: Risk-averse autonomous systems: a brief history and recent developments from the perspective of optimal control
