Imagen de Portada

Optimistic Policy Learning under Pessimistic Adversaries with Regret and Violation Guarantees

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Ganguly, Sourav, Pandit, Kartik, Ghosh, Arnob
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Certifiable Safe RLHF: Fixed-Penalty Constraint Optimization for Safer Language Models
por: Pandit, Kartik, et al.
Publicado: (2025)

Efficient Policy Optimization in Robust Constrained MDPs with Iteration Complexity Guarantees
por: Ganguly, Sourav, et al.
Publicado: (2025)

Tail-Risk-Safe Monte Carlo Tree Search under PAC-Level Guarantees
por: Zhang, Zuyuan, et al.
Publicado: (2025)

Optimistic Regret Bounds for Online Learning in Adversarial Markov Decision Processes
por: Moon, Sang Bin, et al.
Publicado: (2024)

Provably Efficient Sample Complexity for Robust CMDP
por: Ganguly, Sourav, et al.
Publicado: (2025)

Pessimistic Off-Policy Optimization for Learning to Rank
por: Cief, Matej, et al.
Publicado: (2022)

Optimistic Policy Regularization
por: Pham, Mai, et al.
Publicado: (2026)

Kernel-Based Function Approximation for Average Reward Reinforcement Learning: An Optimist No-Regret Algorithm
por: Vakili, Sattar, et al.
Publicado: (2024)

Optimistic Thompson Sampling for No-Regret Learning in Unknown Games
por: Li, Yingru, et al.
Publicado: (2024)

An Optimistic Algorithm for online CMDPS with Anytime Adversarial Constraints
por: Zhu, Jiahui, et al.
Publicado: (2025)

Regret-Based Defense in Adversarial Reinforcement Learning
por: Belaire, Roman, et al.
Publicado: (2023)

Optimistic Model Rollouts for Pessimistic Offline Policy Optimization
por: Zhai, Yuanzhao, et al.
Publicado: (2024)

Data-Driven Online Model Selection With Regret Guarantees
por: Pacchiano, Aldo, et al.
Publicado: (2023)

Minimizing Weighted Counterfactual Regret with Optimistic Online Mirror Descent
por: Xu, Hang, et al.
Publicado: (2024)

Pessimistic Causal Reinforcement Learning with Mediators for Confounded Offline Data
por: Wang, Danyang, et al.
Publicado: (2024)

Optimistic Reinforcement Learning with Quantile Objectives
por: Alipour-Vaezi, Mohammad, et al.
Publicado: (2025)

The Perils of Optimizing Learned Reward Functions: Low Training Error Does Not Guarantee Low Regret
por: Fluri, Lukas, et al.
Publicado: (2024)

Conservative DDPG -- Pessimistic RL without Ensemble
por: Soffair, Nitsan, et al.
Publicado: (2024)

Pessimistic Iterative Planning with RNNs for Robust POMDPs
por: Galesloot, Maris F. L., et al.
Publicado: (2024)

Breaking the Curse of Repulsion: Optimistic Distributionally Robust Policy Optimization for Off-Policy Generative Recommendation
por: Jiang, Jie, et al.
Publicado: (2026)

Optimistic Rates for Learning from Label Proportions
por: Li, Gene, et al.
Publicado: (2024)

Pessimistic Value Iteration for Multi-Task Data Sharing in Offline Reinforcement Learning
por: Bai, Chenjia, et al.
Publicado: (2024)

Restricted Bayesian Neural Network
por: Ganguly, Sourav, et al.
Publicado: (2024)

Global Convergence Guarantees for Federated Policy Gradient Methods with Adversaries
por: Ganesh, Swetha, et al.
Publicado: (2024)

Optimistic Exploration for Risk-Averse Constrained Reinforcement Learning
por: McCarthy, James, et al.
Publicado: (2025)

Diverse Randomized Value Functions: A Provably Pessimistic Approach for Offline Reinforcement Learning
por: Yu, Xudong, et al.
Publicado: (2024)

Learning in Markov Games with Adaptive Adversaries: Policy Regret, Fundamental Barriers, and Efficient Algorithms
por: Nguyen-Tang, Thanh, et al.
Publicado: (2024)

Multi-Step Alignment as Markov Games: An Optimistic Online Gradient Descent Approach with Convergence Guarantees
por: Wu, Yongtao, et al.
Publicado: (2025)

Learning Optimal and Sample-Efficient Decision Policies with Guarantees
por: Shao, Daqian
Publicado: (2026)

Adversarial Environment Design via Regret-Guided Diffusion Models
por: Chung, Hojun, et al.
Publicado: (2024)

Quantum Speedups in Regret Analysis of Infinite Horizon Average-Reward Markov Decision Processes
por: Ganguly, Bhargav, et al.
Publicado: (2023)

No-Regret Learning Under Adversarial Resource Constraints: A Spending Plan Is All You Need!
por: Stradi, Francesco Emanuele, et al.
Publicado: (2025)

Sparse-Reg: Improving Sample Complexity in Offline Reinforcement Learning using Sparsity
por: Arnob, Samin Yeasar, et al.
Publicado: (2025)

Optimistic Gradient Learning with Hessian Corrections for High-Dimensional Black-Box Optimization
por: Kfir, Yedidya, et al.
Publicado: (2025)

Statistical Guarantees in Synthetic Data through Conformal Adversarial Generation
por: Vishwakarma, Rahul, et al.
Publicado: (2025)

Model-Based Proactive Cost Generation for Learning Safe Policies Offline with Limited Violation Data
por: Xue, Ruiqi, et al.
Publicado: (2026)

No-Regret Reinforcement Learning in Smooth MDPs
por: Maran, Davide, et al.
Publicado: (2024)

Implementing Quantum Generative Adversarial Network (qGAN) and QCBM in Finance
por: Ganguly, Santanu
Publicado: (2023)

Guide: Generalized-Prior and Data Encoders for DAG Estimation
por: Roy, Amartya, et al.
Publicado: (2025)

Deep Generative Models for Offline Policy Learning: Tutorial, Survey, and Perspectives on Future Directions
por: Chen, Jiayu, et al.
Publicado: (2024)