English
Related papers

Related papers: A Policy Gradient Algorithm for the Risk-Sensitive…

200 papers

Policy gradients in continuous control have been derived for both stochastic and deterministic policies. Here we study the relationship between the two. In a widely-used family of MDPs involving Gaussian control noise and quadratic control…

Machine Learning · Computer Science 2025-06-11 Emo Todorov

We study the synthesis of a policy in a Markov decision process (MDP) following which an agent reaches a target state in the MDP while minimizing its total discounted cost. The problem combines a reachability criterion with a discounted…

Optimization and Control · Mathematics 2021-03-18 Yagiz Savas , Christos K. Verginis , Michael Hibbard , Ufuk Topcu

The classical policy gradient method is the theoretical and conceptual foundation of modern policy-based reinforcement learning (RL) algorithms. Most rigorous analyses of such methods, particularly those establishing convergence guarantees,…

Machine Learning · Computer Science 2026-02-11 Jongmin Lee , Ernest K. Ryu

We study risk-sensitive reinforcement learning in finite discounted MDPs with recursive entropic risk measures (ERM), where the risk parameter $\beta \neq 0$ controls the agent's risk attitude: $\beta>0$ for risk-averse and $\beta<0$ for…

Machine Learning · Computer Science 2026-05-20 Oliver Mortensen , Mohammad Sadegh Talebi

Risk-sensitive planning aims to identify policies maximizing some tail-focused metrics in Markov Decision Processes (MDPs). Such an optimization task can be very costly for the most widely used and interpretable metrics such as threshold…

Machine Learning · Statistics 2025-07-09 Alexandre Marthe , Samuel Bounan , Aurélien Garivier , Claire Vernade

In this paper, we propose a novel reinforcement- learning algorithm consisting in a stochastic variance-reduced version of policy gradient for solving Markov Decision Processes (MDPs). Stochastic variance-reduced gradient (SVRG) methods…

Machine Learning · Computer Science 2018-06-15 Matteo Papini , Damiano Binaghi , Giuseppe Canonaco , Matteo Pirotta , Marcello Restelli

Policy gradient methods are among the most effective methods in challenging reinforcement learning problems with large state and/or action spaces. However, little is known about even their most basic theoretical convergence properties,…

Machine Learning · Computer Science 2020-10-16 Alekh Agarwal , Sham M. Kakade , Jason D. Lee , Gaurav Mahajan

While there is an extensive body of research analyzing policy gradient methods for discounted cumulative-reward MDPs, prior work on policy gradient methods for average-reward MDPs has been limited, with most existing results restricted to…

Optimization and Control · Mathematics 2026-02-23 Jongmin Lee , Ernest K. Ryu

Several authors have recently developed risk-sensitive policy gradient methods that augment the standard expected cost minimization problem with a measure of variability in cost. These studies have focused on specific risk-measures, such as…

Artificial Intelligence · Computer Science 2015-06-09 Aviv Tamar , Yinlam Chow , Mohammad Ghavamzadeh , Shie Mannor

The goal of policy gradient approaches is to find a policy in a given class of policies which maximizes the expected return. Given a differentiable model of the policy, we want to apply a gradient-ascent technique to reach a local optimum.…

Machine Learning · Computer Science 2019-11-13 Mattis Manfred Kämmerer

We develop policy gradients methods for stochastic control with exit time in a model-free setting. We propose two types of algorithms for learning either directly the optimal policy or by learning alternately the value function (critic) and…

Computational Finance · Quantitative Finance 2023-02-16 Mohamed Hamdouche , Pierre Henry-Labordere , Huyen Pham

Having a perfect model to compute the optimal policy is often infeasible in reinforcement learning. It is important in high-stakes domains to quantify and manage risk induced by model uncertainties. Entropic risk measure is an exponential…

Machine Learning · Computer Science 2020-06-23 Reazul Hasan Russel , Bahram Behzadian , Marek Petrik

We study the offline data-driven sequential decision making problem in the framework of Markov decision process (MDP). In order to enhance the generalizability and adaptivity of the learned policy, we propose to evaluate each policy by a…

Statistics Theory · Mathematics 2021-11-11 Zhengling Qi , Peng Liao

The policy gradient theorem is defined based on an objective with respect to the initial distribution over states. In the discounted case, this results in policies that are optimal for one distribution over initial states, but may not be…

Machine Learning · Computer Science 2019-12-12 Riashat Islam , Raihan Seraj , Pierre-Luc Bacon , Doina Precup

Markov decision processes (MDPs) is viewed as an optimization of an objective function over certain linear operators over general function spaces. A new existence result is established for the existence of optimal policies in general MDPs,…

Machine Learning · Computer Science 2026-04-01 Abhishek Gupta , Aditya Mahajan

This paper discusses theoretical and experimental aspects of gradient-based approaches to the direct optimization of policy performance in controlled POMDPs. We introduce GPOMDP, a REINFORCE-like algorithm for estimating an approximation to…

Machine Learning · Computer Science 2025-12-08 Jonathan Baxter , Peter L. Bartlett

This paper proposes an iterative distributionally robust model predictive control (MPC) scheme to solve a risk-constrained infinite-horizon optimal control problem. In each iteration, the algorithm generates a trajectory from the starting…

Optimization and Control · Mathematics 2023-08-23 Alireza Zolanvari , Ashish Cherukuri

We study a risk-constrained version of the stochastic shortest path (SSP) problem, where the risk measure considered is Conditional Value-at-Risk (CVaR). We propose two algorithms that obtain a locally risk-optimal policy by employing four…

Machine Learning · Statistics 2018-10-23 Prashanth L. A.

In this paper, we consider a modified version of the control problem in a model free Markov decision process (MDP) setting with large state and action spaces. The control problem most commonly addressed in the contemporary literature is to…

Artificial Intelligence · Computer Science 2018-02-01 Ajin George Joseph , Shalabh Bhatnagar

Policy gradient methods in reinforcement learning update policy parameters by taking steps in the direction of an estimated gradient of policy value. In this paper, we consider the statistically efficient estimation of policy gradients from…

Machine Learning · Statistics 2020-02-21 Nathan Kallus , Masatoshi Uehara