Learning Infinite-Horizon Average-Reward CMDPs via State Augmentation
cs.LG
Submitted: 2026-09-30
Updated: 2026-09-30
Sources
- Scalable Constrained Multi-Agent Reinforcement Learning via State Augmentation and Consensus for Separable Dynamics
- Efficient Reinforcement Learning in Factored MDPs with Application to Constrained RL
- A Primal-Dual Approach to Constrained Markov Decision Processes
- Exploration-Exploitation in Constrained MDPs
- Regret Analysis of Unichain Average Reward Constrained MDPs with General Parameterization
- Learning in Markov Decision Processes under Constraints
- Learning Weakly Communicating Average-Reward CMDPs: Strong Duality and Improved Regret
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: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks