Near-Optimal Primal-Dual Algorithm for Learning Linear Mixture CMDPs with Adversarial Rewards

arXiv:2603.27884 · cs.LG, math.OC · Submitted 2026-03-29 · Read on arXiv

cs.LG, math.OC

Submitted: 2026-03-29

Updated: 2026-09-18

Code: https://github.com/kihyun-yu/pd-powers

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Regret — 38× in this paper · explained in 3 episodes
• Reinforcement Learning — 13× in this paper · explained in 4 episodes
• Sample Complexity — 4× in this paper · explained in 15 episodes
• Regularization — 3× in this paper · explained in 3 episodes
• Reward Function — 3× in this paper · explained in 2 episodes
• Action Space — 1× in this paper · explained in 1 episode
• Generative Model — 1× in this paper · explained in 2 episodes
• Heteroscedasticity — 1× in this paper · explained in 2 episodes
• Minimax Regret — 1× in this paper · explained in 2 episodes
• Q-learning — 1× in this paper · explained in 3 episodes
• Theoretical Guarantees — 1× in this paper · explained in 2 episodes

Sources

• Exploration-Exploitation in Constrained MDPs
• Provably Efficient RL under Episode-Wise Safety in Constrained MDPs with Linear Function Approximation
• Sample Complexity Bounds for Linear Constrained MDPs with a Generative Model

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks