English
Related papers

Related papers: Risk-Averse Bayes-Adaptive Reinforcement Learning

200 papers

Bayesian inference over the reward presents an ideal solution to the ill-posed nature of the inverse reinforcement learning problem. Unfortunately current methods generally do not scale well beyond the small tabular setting due to the need…

Machine Learning · Computer Science 2021-03-15 Alex J. Chan , Mihaela van der Schaar

Maneuver decision-making can be regarded as a Markov decision process and can be address by reinforcement learning. However, original reinforcement learning algorithms can hardly solve the maneuvering decision-making problem. One reason is…

Artificial Intelligence · Computer Science 2023-09-19 Zhang Hong-Peng

A Markov Decision Process (MDP) is a popular model for reinforcement learning. However, its commonly used assumption of stationary dynamics and rewards is too stringent and fails to hold in adversarial, nonstationary, or multi-agent…

Machine Learning · Computer Science 2019-08-22 Tiancheng Yu , Suvrit Sra

Stochastic domains often involve risk-averse decision makers. While recent work has focused on how to model risk in Markov decision processes using risk measures, it has not addressed the problem of solving large risk-averse formulations.…

Portfolio Management · Quantitative Finance 2012-10-19 Marek Petrik , Dharmashankar Subramanian

In the reinforcement learning literature, there are many algorithms developed for either Contextual Bandit (CB) or Markov Decision Processes (MDP) environments. However, when deploying reinforcement learning algorithms in the real world,…

Machine Learning · Computer Science 2022-08-02 Kelly W. Zhang , Omer Gottesman , Finale Doshi-Velez

Robot navigation in dynamic, crowded environments poses a significant challenge due to the inherent uncertainties in the obstacle model. In this work, we propose a risk-adaptive approach based on the Conditional Value-at-Risk Barrier…

Robotics · Computer Science 2025-08-04 Xinyi Wang , Taekyung Kim , Bardh Hoxha , Georgios Fainekos , Dimitra Panagou

We propose a convex formulation for a trading system with the Conditional Value-at-Risk as a risk-adjusted performance measure under the notion of Direct Reinforcement Learning. Due to convexity, the proposed approach can uncover a…

Trading and Market Microstructure · Quantitative Finance 2021-09-30 Ali Al-Ameer , Khaled Alshehri

This study investigates the mean-variance (MV) trade-off in reinforcement learning (RL), an instance of the sequential decision-making under uncertainty. Our objective is to obtain MV-efficient policies whose means and variances are located…

Machine Learning · Computer Science 2024-11-14 Masahiro Kato , Kei Nakagawa , Kenshi Abe , Tetsuro Morimura , Kentaro Baba

Offline reinforcement learning (RL) is a powerful approach for data-driven decision-making and control. Compared to model-free methods, offline model-based reinforcement learning (MBRL) explicitly learns world models from a static dataset…

Machine Learning · Computer Science 2026-01-28 Jiayu Chen , Le Xu , Wentse Chen , Jeff Schneider

Solving chance-constrained optimal control problems for systems subject to non-stationary uncertainties is a significant challenge.Conventional robust model predictive control (MPC) often yields excessive conservatism by relying on static…

Systems and Control · Electrical Eng. & Systems 2025-07-16 Mingcong Li

In risk-averse reinforcement learning (RL), the goal is to optimize some risk measure of the returns. A risk measure often focuses on the worst returns out of the agent's experience. As a result, standard methods for risk-averse RL often…

Machine Learning · Computer Science 2022-10-13 Ido Greenberg , Yinlam Chow , Mohammad Ghavamzadeh , Shie Mannor

This paper proposes a safety analysis method that facilitates a tunable balance between the worst-case and risk-neutral perspectives. First, we define a risk-sensitive safe set to specify the degree of safety attained by a stochastic…

Systems and Control · Electrical Eng. & Systems 2020-07-28 Margaret P. Chapman , Jonathan P. Lacotte , Kevin M. Smith , Insoon Yang , Yuxi Han , Marco Pavone , Claire J. Tomlin

We study a continuous-time portfolio optimization problem under an explicit constraint on the Deviation Conditional Value-at-Risk (DCVaR), defined as the difference between the CVaR and the expected terminal wealth. While the mean-CVaR…

Optimization and Control · Mathematics 2025-10-01 Jérôme Lelong , Véronique Maume-Deschamps , William Thevenot

The problem of finding the optimal portfolio for investors is called the portfolio optimization problem. Such problem mainly concerns the expectation and variability of return (i.e., mean and variance). Although the variance would be the…

Portfolio Management · Quantitative Finance 2020-07-21 Kei Nakagawa , Shuhei Noma , Masaya Abe

This article develops a new algorithm named TTRISK to solve high-dimensional risk-averse optimization problems governed by differential equations (ODEs and/or PDEs) under uncertainty. As an example, we focus on the so-called Conditional…

Numerical Analysis · Mathematics 2022-12-02 Harbir Antil , Sergey Dolgov , Akwum Onwunta

In stochastic games with incomplete information, the uncertainty is evoked by the lack of knowledge about a player's own and the other players' types, i.e. the utility function and the policy space, and also the inherent stochasticity of…

Machine Learning · Computer Science 2022-03-21 Hannes Eriksson , Debabrota Basu , Mina Alibeigi , Christos Dimitrakakis

The goal of Bayesian inverse reinforcement learning (IRL) is recovering a posterior distribution over reward functions using a set of demonstrations from an expert optimizing for a reward unknown to the learner. The resulting posterior over…

Machine Learning · Computer Science 2024-07-16 Ondrej Bajgar , Alessandro Abate , Konstantinos Gatsis , Michael A. Osborne

In Offline Model Learning for Planning and in Offline Reinforcement Learning, the limited data set hinders the estimate of the Value function of the relative Markov Decision Process (MDP). Consequently, the performance of the obtained…

Machine Learning · Computer Science 2026-05-26 Giorgio Angelotti , Nicolas Drougard , Caroline Ponzoni Carvalho Chanel

We use the Reward Biased Maximum Likelihood Estimation (RBMLE) algorithm to learn optimal policies for constrained Markov Decision Processes (CMDPs). We analyze the learning regrets of RBMLE.

Optimization and Control · Mathematics 2021-05-31 Rahul Singh

We consider infinite-horizon Markov Decision Processes where parameters, such as transition probabilities, are unknown and estimated from data. The popular distributionally robust approach to addressing the parameter uncertainty can…

Systems and Control · Electrical Eng. & Systems 2024-12-23 Yifan Lin , Enlu Zhou