Near-Minimax Sample Complexity for Multi-Objective Reinforcement Learning under Generative Models
stat.ML, cs.LG
Submitted: 2026-11-03
Updated: 2026-11-03
Terminology
Sources
- Breaking the Sample Size Barrier in Model-Based Reinforcement Learning with a Generative Model
- Provable Multi-Objective Reinforcement Learning with Generative Models
- Optimal Multi-Reward Reinforcement Learning
- How to Find the Exact Pareto Front for Multi-Objective MDPs?
- Finite-Time Convergence and Sample Complexity of Actor-Critic Multi-Objective Reinforcement Learning
- Scaling Pareto-Efficient Decision Making Via Offline Multi-Objective RL
- Traversing Pareto Optimal Policies: Provably Efficient Multi-Objective Reinforcement Learning
- Improved Bounds for Reward-Agnostic and Reward-Free Exploration
- Empirical Bernstein Bounds and Sample Variance Penalization
Related papers
- Uniform-in-Time Weak Propagation-of-Chaos in Shallow Neural Networks
- Diffusion Models Observe Only Gradients: A Geometric Perspective on Score Matching Errors
- Quantifying Error Propagation and Model Collapse in Diffusion Models
- Behavior of prediction performance metrics with rare events
- Statistical Inference and Learning for Shapley Additive Explanations (SHAP)
- Control Variate Design for Score-Function Gradient Estimators in Importance-Weighted Variational Inference