Cover Image

Improved Regret Bound for Safe Reinforcement Learning via Tighter Cost Pessimism and Reward Optimism

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yu, Kihyun, Lee, Duksang, Overman, William, Lee, Dabeen
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Optimization and Control
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Learning Weakly Communicating Average-Reward CMDPs: Strong Duality and Improved Regret
by: Yu, Kihyun, et al.
Published: (2026)

Near-Optimal Primal-Dual Algorithm for Learning Linear Mixture CMDPs with Adversarial Rewards
by: Yu, Kihyun, et al.
Published: (2026)

Provably Efficient Infinite-Horizon Average-Reward Reinforcement Learning with Linear Function Approximation
by: Chae, Woojin, et al.
Published: (2024)

Learning Infinite-Horizon Average-Reward Linear Mixture MDPs of Bounded Span
by: Chae, Woojin, et al.
Published: (2024)

Infinite-Horizon Reinforcement Learning with Multinomial Logistic Function Approximation
by: Park, Jaehyun, et al.
Published: (2024)

Parameter-Free Algorithms for Performative Regret Minimization under Decision-Dependent Distributions
by: Park, Sungwoo, et al.
Published: (2024)

Stochastic-Constrained Stochastic Optimization with Markovian Data
by: Kim, Yeongjong, et al.
Published: (2023)

Reinforcement Learning and Regret Bounds for Admission Control
by: Weber, Lucas, et al.
Published: (2024)

Optimism as Risk-Seeking in Multi-Agent Reinforcement Learning
by: Zhang, Runyu, et al.
Published: (2025)

Faster Rates for No-Regret Learning in General Games via Cautious Optimism
by: Soleymani, Ashkan, et al.
Published: (2025)

Pessimism Meets Risk: Risk-Sensitive Offline Reinforcement Learning
by: Zhang, Dake, et al.
Published: (2024)

Improving Online-to-Nonconvex Conversion for Smooth Optimization via Double Optimism
by: Patitucci, Francisco, et al.
Published: (2025)

Online (Non-)Convex Learning via Tempered Optimism
by: Haddouche, Maxime, et al.
Published: (2023)

Chebyshev Center-Based Direction Selection for Multi-Objective Optimization and Training PINNs
by: Yoon, Hoyeol, et al.
Published: (2026)

Tail Distribution of Regret in Optimistic Reinforcement Learning
by: Khodadadian, Sajad, et al.
Published: (2025)

Regret Lower Bounds for Learning Linear Quadratic Gaussian Systems
by: Ziemann, Ingvar, et al.
Published: (2022)

Rate-Optimal Regret for the Safe Learning-based Control of the Constrained Linear Quadratic Regulator
by: Hutchinson, Spencer, et al.
Published: (2026)

Achieving Tractable Minimax Optimal Regret in Average Reward MDPs
by: Boone, Victor, et al.
Published: (2024)

Cautious Optimism: A Meta-Algorithm for Near-Constant Regret in General Games
by: Soleymani, Ashkan, et al.
Published: (2025)

Tighter Performance Theory of FedExProx
by: Anyszka, Wojciech, et al.
Published: (2024)

Regret Bounds for Episodic Risk-Sensitive Linear Quadratic Regulator
by: Xu, Wenhao, et al.
Published: (2024)

Variance-Aware Regret Bounds for Stochastic Contextual Dueling Bandits
by: Di, Qiwei, et al.
Published: (2023)

Implicit Riemannian Optimism with Applications to Min-Max Problems
by: Roux, Christophe, et al.
Published: (2025)

Regret Bounds for Expected Improvement Algorithms in Gaussian Process Bandit Optimization
by: Tran-The, Hung, et al.
Published: (2022)

Reward-Relevance-Filtered Linear Offline Reinforcement Learning
by: Zhou, Angela
Published: (2024)

Achieving Better Local Regret Bound for Online Non-Convex Bilevel Optimization
by: Jia, Tingkai, et al.
Published: (2026)

Optimistic Online LQR via Intrinsic Rewards
by: Bartos, Marcell, et al.
Published: (2026)

Identification and Adaptive Control of Markov Jump Systems: Sample Complexity and Regret Bounds
by: Sattar, Yahya, et al.
Published: (2021)

Offline Reinforcement Learning via Linear-Programming with Error-Bound Induced Constraints
by: Ozdaglar, Asuman, et al.
Published: (2022)

Sublinear Regret for a Class of Continuous-Time Linear-Quadratic Reinforcement Learning Problems
by: Huang, Yilie, et al.
Published: (2024)

Sampling-based Safe Reinforcement Learning for Nonlinear Dynamical Systems
by: Suttle, Wesley A., et al.
Published: (2024)

Sample Complexity of Distributionally Robust Average-Reward Reinforcement Learning
by: Chen, Zijun, et al.
Published: (2025)

Online Optimization on Hadamard Manifolds: Curvature Independent Regret Bounds on Horospherically Convex Objectives
by: Sahinoglu, Emre, et al.
Published: (2025)

Tight Regret Bounds for Bayesian Optimization in One Dimension
by: Scarlett, Jonathan
Published: (2018)

Methodology for Interpretable Reinforcement Learning for Optimizing Mechanical Ventilation
by: Lee, Joo Seung, et al.
Published: (2024)

Safe Reinforcement Learning for Constrained Markov Decision Processes with Stochastic Stopping Time
by: Mazumdar, Abhijit, et al.
Published: (2024)

Quotient-Categorical Representations for Bellman-Compatible Average-Reward Distributional Reinforcement Learning
by: Kaya, Ege C., et al.
Published: (2026)

Dynamic Regret via Discounted-to-Dynamic Reduction with Applications to Curved Losses and Adam Optimizer
by: Xie, Yan-Feng, et al.
Published: (2026)

Learning Decentralized Linear Quadratic Regulators with $\sqrt{T}$ Regret
by: Ye, Lintao, et al.
Published: (2022)

Optimal Variance-Dependent Regret Bounds for Infinite-Horizon MDPs
by: Zamir, Guy, et al.
Published: (2026)