Image de couverture de livre

Optimistic Policy Learning under Pessimistic Adversaries with Regret and Violation Guarantees

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Ganguly, Sourav, Pandit, Kartik, Ghosh, Arnob
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Certifiable Safe RLHF: Fixed-Penalty Constraint Optimization for Safer Language Models
par: Pandit, Kartik, et autres
Publié: (2025)

Efficient Policy Optimization in Robust Constrained MDPs with Iteration Complexity Guarantees
par: Ganguly, Sourav, et autres
Publié: (2025)

Tail-Risk-Safe Monte Carlo Tree Search under PAC-Level Guarantees
par: Zhang, Zuyuan, et autres
Publié: (2025)

Optimistic Regret Bounds for Online Learning in Adversarial Markov Decision Processes
par: Moon, Sang Bin, et autres
Publié: (2024)

Provably Efficient Sample Complexity for Robust CMDP
par: Ganguly, Sourav, et autres
Publié: (2025)

Pessimistic Off-Policy Optimization for Learning to Rank
par: Cief, Matej, et autres
Publié: (2022)

Optimistic Policy Regularization
par: Pham, Mai, et autres
Publié: (2026)

Kernel-Based Function Approximation for Average Reward Reinforcement Learning: An Optimist No-Regret Algorithm
par: Vakili, Sattar, et autres
Publié: (2024)

Optimistic Thompson Sampling for No-Regret Learning in Unknown Games
par: Li, Yingru, et autres
Publié: (2024)

An Optimistic Algorithm for online CMDPS with Anytime Adversarial Constraints
par: Zhu, Jiahui, et autres
Publié: (2025)

Regret-Based Defense in Adversarial Reinforcement Learning
par: Belaire, Roman, et autres
Publié: (2023)

Optimistic Model Rollouts for Pessimistic Offline Policy Optimization
par: Zhai, Yuanzhao, et autres
Publié: (2024)

Data-Driven Online Model Selection With Regret Guarantees
par: Pacchiano, Aldo, et autres
Publié: (2023)

Minimizing Weighted Counterfactual Regret with Optimistic Online Mirror Descent
par: Xu, Hang, et autres
Publié: (2024)

Pessimistic Causal Reinforcement Learning with Mediators for Confounded Offline Data
par: Wang, Danyang, et autres
Publié: (2024)

Optimistic Reinforcement Learning with Quantile Objectives
par: Alipour-Vaezi, Mohammad, et autres
Publié: (2025)

The Perils of Optimizing Learned Reward Functions: Low Training Error Does Not Guarantee Low Regret
par: Fluri, Lukas, et autres
Publié: (2024)

Conservative DDPG -- Pessimistic RL without Ensemble
par: Soffair, Nitsan, et autres
Publié: (2024)

Pessimistic Iterative Planning with RNNs for Robust POMDPs
par: Galesloot, Maris F. L., et autres
Publié: (2024)

Breaking the Curse of Repulsion: Optimistic Distributionally Robust Policy Optimization for Off-Policy Generative Recommendation
par: Jiang, Jie, et autres
Publié: (2026)

Optimistic Rates for Learning from Label Proportions
par: Li, Gene, et autres
Publié: (2024)

Pessimistic Value Iteration for Multi-Task Data Sharing in Offline Reinforcement Learning
par: Bai, Chenjia, et autres
Publié: (2024)

Restricted Bayesian Neural Network
par: Ganguly, Sourav, et autres
Publié: (2024)

Global Convergence Guarantees for Federated Policy Gradient Methods with Adversaries
par: Ganesh, Swetha, et autres
Publié: (2024)

Optimistic Exploration for Risk-Averse Constrained Reinforcement Learning
par: McCarthy, James, et autres
Publié: (2025)

Diverse Randomized Value Functions: A Provably Pessimistic Approach for Offline Reinforcement Learning
par: Yu, Xudong, et autres
Publié: (2024)

Learning in Markov Games with Adaptive Adversaries: Policy Regret, Fundamental Barriers, and Efficient Algorithms
par: Nguyen-Tang, Thanh, et autres
Publié: (2024)

Multi-Step Alignment as Markov Games: An Optimistic Online Gradient Descent Approach with Convergence Guarantees
par: Wu, Yongtao, et autres
Publié: (2025)

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

Adversarial Environment Design via Regret-Guided Diffusion Models
par: Chung, Hojun, et autres
Publié: (2024)

Quantum Speedups in Regret Analysis of Infinite Horizon Average-Reward Markov Decision Processes
par: Ganguly, Bhargav, et autres
Publié: (2023)

No-Regret Learning Under Adversarial Resource Constraints: A Spending Plan Is All You Need!
par: Stradi, Francesco Emanuele, et autres
Publié: (2025)

Sparse-Reg: Improving Sample Complexity in Offline Reinforcement Learning using Sparsity
par: Arnob, Samin Yeasar, et autres
Publié: (2025)

Optimistic Gradient Learning with Hessian Corrections for High-Dimensional Black-Box Optimization
par: Kfir, Yedidya, et autres
Publié: (2025)

Statistical Guarantees in Synthetic Data through Conformal Adversarial Generation
par: Vishwakarma, Rahul, et autres
Publié: (2025)

Model-Based Proactive Cost Generation for Learning Safe Policies Offline with Limited Violation Data
par: Xue, Ruiqi, et autres
Publié: (2026)

No-Regret Reinforcement Learning in Smooth MDPs
par: Maran, Davide, et autres
Publié: (2024)

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

Guide: Generalized-Prior and Data Encoders for DAG Estimation
par: Roy, Amartya, et autres
Publié: (2025)

Deep Generative Models for Offline Policy Learning: Tutorial, Survey, and Perspectives on Future Directions
par: Chen, Jiayu, et autres
Publié: (2024)