Finite-Sample Convergence in Networked Average Reward MARL: Decentralization Pitfalls and Entropy Remedies
cs.LG, cs.MA
Submitted: 2026-11-02
Updated: 2026-11-07
Terminology
Sources
- Revisiting Policy Gradients for Restricted Policy Classes: Escaping Myopic Local Optima with $k$-step Policy Gradients
- High entropy leads to symmetry-equivariant policies in Dec-POMDPs
- A Policy Gradient Method for Confounded POMDPs
- Multi-Agent Reinforcement Learning for Energy Networks: Computational Challenges, Progress and Open Problems
- Performance of NPG in Countable State-Space Average-Cost RL
- Proximal Policy Optimization Algorithms
Related papers
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis
- (Mis)generalization of Helpful-Only Fine-tuning