English
Related papers

Related papers: Value-Distributional Model-Based Reinforcement Lea…

200 papers

Temporal-Difference (TD) learning methods, such as Q-Learning, have proven effective at learning a policy to perform control tasks. One issue with methods like Q-Learning is that the value update introduces bias when predicting the TD…

Machine Learning · Computer Science 2021-10-29 Litian Liang , Yaosheng Xu , Stephen McAleer , Dailin Hu , Alexander Ihler , Pieter Abbeel , Roy Fox

Sequential decision making in the presence of uncertainty and stochastic dynamics gives rise to distributions over state/action trajectories in reinforcement learning (RL) and optimal control problems. This observation has led to a variety…

Machine Learning · Computer Science 2021-09-30 Jad Rahme , Ryan P. Adams

Tail-end risk measures such as static conditional value-at-risk (CVaR) are used in safety-critical applications to prevent rare, yet catastrophic events. Unlike risk-neutral objectives, the static CVaR of the return depends on entire…

Machine Learning · Computer Science 2026-02-04 Aneri Muni , Vincent Taboga , Esther Derman , Pierre-Luc Bacon , Erick Delage

Given a multivariate function taking deterministic and uncertain inputs, we consider the problem of estimating a quantile set: a set of deterministic inputs for which the probability that the output belongs to a specific region remains…

Applications · Statistics 2025-07-25 Romain Ait Abdelmalek-Lomenech , Julien Bect , Emmanuel Vazquez

It is desirable to have accurate uncertainty estimation from a single deterministic forward-pass model, as traditional methods for uncertainty quantification are computationally expensive. However, this is difficult because single…

Machine Learning · Computer Science 2023-08-22 Frederik Boe Hüttel , Filipe Rodrigues , Francisco Câmara Pereira

Reinforcement learning from human feedback (RLHF) has become a key method for aligning large language models (LLMs) with human preferences through the use of reward models. However, traditional reward models typically generate point…

Machine Learning · Computer Science 2024-09-17 Nicolai Dorka

Uncertainty quantification is one of the central challenges for machine learning in real-world applications. In reinforcement learning, an agent confronts two kinds of uncertainty, called epistemic uncertainty and aleatoric uncertainty.…

Machine Learning · Computer Science 2023-07-06 Takuya Kanazawa , Haiyan Wang , Chetan Gupta

Offline reinforcement learning learns policies from fixed datasets without further environment interaction. A key challenge in this setting is epistemic uncertainty, arising from limited or biased data coverage, particularly when the…

Machine Learning · Computer Science 2026-04-09 Abhilash Reddy Chenreddy , Erick Delage

Reinforcement learning (RL) tackles sequential decision-making problems by creating agents that interacts with their environment. However, existing algorithms often view these problem as static, focusing on point estimates for model…

Machine Learning · Statistics 2024-03-21 Frank Shih , Faming Liang

Deep Q-learning jointly learns representations and values within monolithic networks, promising beneficial co-adaptation between features and value estimates. Although this architecture has attained substantial success, the coupling between…

Machine Learning · Computer Science 2026-01-30 Fernando Martinez , Tao Li , Yingdong Lu , Juntao Chen

In this paper, we study distributional reinforcement learning from the perspective of statistical efficiency. We investigate distributional policy evaluation, aiming to estimate the complete return distribution (denoted $\eta^\pi$) attained…

Machine Learning · Statistics 2025-11-13 Liangyu Zhang , Yang Peng , Jiadong Liang , Wenhao Yang , Zhihua Zhang

In traditional reinforcement learning, an agent maximizes the reward collected during its interaction with the environment by approximating the optimal policy through the estimation of value functions. Typically, given a state s and action…

Machine Learning · Computer Science 2018-06-20 Shangda Li , Selina Bing , Steven Yang

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

We consider the problem of learning models for risk-sensitive reinforcement learning. We theoretically demonstrate that proper value equivalence, a method of learning models which can be used to plan optimally in the risk-neutral setting,…

Machine Learning · Computer Science 2023-12-05 Tyler Kastner , Murat A. Erdogdu , Amir-massoud Farahmand

Model-Based Reinforcement Learning (RL) is widely believed to have the potential to improve sample efficiency by allowing an agent to synthesize large amounts of imagined experience. Experience Replay (ER) can be considered a simple kind of…

Machine Learning · Computer Science 2023-07-11 Kenny Young , Aditya Ramesh , Louis Kirsch , Jürgen Schmidhuber

We present a novel statistical approach to incorporating uncertainty awareness in model-free distributional reinforcement learning involving quantile regression-based deep Q networks. The proposed algorithm, $\textit{Calibrated Evidential…

Machine Learning · Computer Science 2024-06-05 Alex Christopher Stutts , Danilo Erricolo , Theja Tulabandhula , Amit Ranjan Trivedi

Conditional value-at-risk (CVaR) is a prominent risk measure in financial engineering, energy systems, and supply chain management. In these domains, Markov decision processes (MDPs) with a long-run CVaR criterion effectively mitigate cost…

Optimization and Control · Mathematics 2026-03-11 Qixin Wang , Hao Cao , Jian-Qiang Hu , Mingjie Hu , Li Xia

A key problem in the theory of meta-learning is to understand how the task distributions influence transfer risk, the expected error of a meta-learner on a new task drawn from the unknown task distribution. In this paper, focusing on fixed…

Machine Learning · Statistics 2021-06-15 Mikhail Konobeev , Ilja Kuzborskij , Csaba Szepesvári

A Markov decision process can be parameterized by a transition kernel and a reward function. Both play essential roles in the study of reinforcement learning as evidenced by their presence in the Bellman equations. In our inquiry of various…

Machine Learning · Computer Science 2023-09-04 Falcon Z. Dai

Distributional reinforcement learning (RL) has proven useful in multiple benchmarks as it enables approximating the full distribution of returns and extracts rich feedback from environment samples. The commonly used quantile regression…

Machine Learning · Computer Science 2025-05-27 Sami Jullien , Romain Deffayet , Jean-Michel Renders , Paul Groth , Maarten de Rijke