English
Related papers

Related papers: Model-Based Epistemic Variance of Values for Risk-…

200 papers

We investigate statistical uncertainty quantification for reinforcement learning (RL) and its implications in exploration policy. Despite ever-growing literature on RL applications, fundamental questions about inference and error…

Machine Learning · Computer Science 2022-12-06 YI Zhu , Jing Dong , Henry Lam

Exploration in reinforcement learning is a challenging problem: in the worst case, the agent must search for high-reward states that could be hidden anywhere in the state space. Can we define a more tractable class of RL problems, where the…

Machine Learning · Computer Science 2021-07-20 Kevin Li , Abhishek Gupta , Ashwin Reddy , Vitchyr Pong , Aurick Zhou , Justin Yu , Sergey Levine

In a sequential decision-making problem, off-policy evaluation estimates the expected cumulative reward of a target policy using logged trajectory data generated from a different behavior policy, without execution of the target policy.…

Machine Learning · Computer Science 2022-11-04 Jie Wang , Rui Gao , Hongyuan Zha

We consider finite-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 sometimes…

Systems and Control · Electrical Eng. & Systems 2022-10-07 Yifan Lin , Yuxuan Ren , Enlu Zhou

Traditional reinforcement learning (RL) aims to maximize the expected total reward, while the risk of uncertain outcomes needs to be controlled to ensure reliable performance in a risk-averse setting. In this paper, we consider the problem…

Machine Learning · Computer Science 2023-01-18 Xian Yu , Siqian Shen

In a discounted reward Markov Decision Process (MDP), the objective is to find the optimal value function, i.e., the value function corresponding to an optimal policy. This problem reduces to solving a functional equation known as the…

Machine Learning · Computer Science 2019-06-17 Chandramouli Kamanchi , Raghuram Bharadwaj Diddigi , Shalabh Bhatnagar

Fairness plays a crucial role in various multi-agent systems (e.g., communication networks, financial markets, etc.). Many multi-agent dynamical interactions can be cast as Markov Decision Processes (MDPs). While existing research has…

Machine Learning · Computer Science 2023-06-02 Peizhong Ju , Arnob Ghosh , Ness B. Shroff

This paper addresses objectives tailored to the risk-averse optimization of accumulated rewards in Markov decision processes (MDPs). The studied objectives require maximizing the expected value of the accumulated rewards minus a penalty…

Logic in Computer Science · Computer Science 2024-07-10 Christel Baier , Jakob Piribauer , Maximilian Starke

We present a reinforcement learning (RL) approach for robust optimisation of risk-aware performance criteria. To allow agents to express a wide variety of risk-reward profiles, we assess the value of a policy using rank dependent expected…

Machine Learning · Computer Science 2021-12-16 Sebastian Jaimungal , Silvana Pesenti , Ye Sheng Wang , Hariom Tatsat

The parameters for a Markov Decision Process (MDP) often cannot be specified exactly. Uncertain MDPs (UMDPs) capture this model ambiguity by defining sets which the parameters belong to. Minimax regret has been proposed as an objective for…

Artificial Intelligence · Computer Science 2023-02-14 Marc Rigter , Bruno Lacerda , Nick Hawes

Many reinforcement learning algorithms rely on value estimation, however, the most widely used algorithms -- namely temporal difference algorithms -- can diverge under both off-policy sampling and nonlinear function approximation. Many…

Machine Learning · Computer Science 2024-08-02 Andrew Patterson , Adam White , Martha White

Reinforcement learning systems are often concerned with balancing exploration of untested actions against exploitation of actions that are known to be good. The benefit of exploration can be estimated using the classical notion of Value of…

Artificial Intelligence · Computer Science 2013-01-30 Richard Dearden , Nir Friedman , David Andre

Model-free reinforcement learning based methods such as Proximal Policy Optimization, or Q-learning typically require thousands of interactions with the environment to approximate the optimum controller which may not always be feasible in…

Machine Learning · Computer Science 2019-05-16 Narendra Patwardhan , Zequn Wang

The Best Estimate plus Uncertainty (BEPU) approach for nuclear systems modeling and simulation requires that the prediction uncertainty must be quantified in order to prove that the investigated design stays within acceptance criteria. A…

Computation · Statistics 2023-03-24 Ziyu Xie , Farah Alsafadi , Xu Wu

Prioritized experience replay, which improves sample efficiency by selecting relevant transitions to update parameter estimates, is a crucial component of contemporary value-based deep reinforcement learning models. Typically, transitions…

Machine Learning · Computer Science 2025-06-12 Rodrigo Carrasco-Davis , Sebastian Lee , Claudia Clopath , Will Dabney

Learning and optimal control under robust Markov decision processes (MDPs) have received increasing attention, yet most existing theory, algorithms, and applications focus on finite-horizon or discounted models. Long-run average-reward…

Optimization and Control · Mathematics 2025-12-12 Shengbo Wang , Nian Si

Bus holding control is challenging due to stochastic traffic and passenger demand. While deep reinforcement learning (DRL) shows promise, standard actor-critic algorithms suffer from Q-value instability in volatile environments. A key…

Machine Learning · Computer Science 2026-05-20 Yifan Zhang , Liang Zheng

Uncertainty Quantification (UQ) is essential in probabilistic machine learning models, particularly for assessing the reliability of predictions. In this paper, we present a systematic framework for estimating both epistemic and aleatoric…

Machine Learning · Statistics 2025-09-11 Marzieh Ajirak , Anand Ravishankar , Petar M. Djuric

We study the exploration problem with approximate linear action-value functions in episodic reinforcement learning under the notion of low inherent Bellman error, a condition normally employed to show convergence of approximate value…

Machine Learning · Computer Science 2020-06-30 Andrea Zanette , Alessandro Lazaric , Mykel Kochenderfer , Emma Brunskill

Value-based reinforcement-learning algorithms have shown strong results in games, robotics, and other real-world applications. Overestimation bias is a known threat to those algorithms and can sometimes lead to dramatic performance…

Machine Learning · Computer Science 2024-08-13 Martin Waltz , Ostap Okhrin