Average-Reward Policy Identification from a Single Continuing Trajectory

cs.LG

Submitted: 2026-10-14

Updated: 2026-10-14

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

Sources

• Sample Complexity of Average-Reward Q-Learning: From Single-agent to Federated Reinforcement Learning
• Non-Asymptotic Best Policy Identification Guarantees in Online Reinforcement Learning
• Learning Policy from a Single Trajectory in Average-Reward Markov Decision Process
• Near Sample-Optimal Reduction-based Policy Learning for Average Reward MDP

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