Research map / Reinforcement learning / Policy gradient and actor-critic
MDPGT: Momentum-Based Decentralized Policy Gradient Tracking
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use mini-batch rather than single-trajectory initialization (ablation) | MDPGT · Decentralized MARL | sampling complexity: \mathcal{O}(N^{-1}\epsilon^{-4}) -> \mathcal{O}(N^{-1}\epsilon^{-3}) | Helped |
| Use MDPGT instead of DPG | Cooperative navigation, five agents · Cooperative navigation gridworld | average reward | Helped |
| Use MDPGT instead of MDPG | Cooperative navigation, five agents · Cooperative navigation gridworld | average reward | Helped |
| Lower the momentum coefficient to 0.2 or 0.3 (ablation) | MDPGT · Cooperative navigation gridworld | average reward | Mixed |
| Raise the momentum coefficient until the surrogate degenerates toward vanilla policy gradients (ablation) | MDPGT · Cooperative navigation gridworld | average reward | Hurt |
| Use fully connected, ring, or bi-partite communication topology (ablation) | MDPGT · Cooperative navigation gridworld, five agents | average reward | No clear effect |
Closest papers by meaning
- Consensus Based Stochastic Optimal Control (ICML 2025 · similarity 0.88)
- Towards Global Optimality for Practical Average Reward Reinforcement Learning without Mixing Time Oracles (ICML 2024 · similarity 0.87)
- Natural Policy Gradient as Doubly Smoothed Policy Iteration: A Bellman-Operator Framework (NeurIPS 2026 · similarity 0.87)
- Accelerated Policy Gradient: On the Convergence Rates of the Nesterov Momentum for Reinforcement Learning (ICML 2024 · similarity 0.87)
- Momentum for the Win: Collaborative Federated Reinforcement Learning across Heterogeneous Environments (ICML 2024 · similarity 0.86)
- Diffusion Policy Policy Optimization (ICLR 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.