Research map / Reinforcement learning / Policy gradient and actor-critic
Damped Anderson Mixing for Deep Reinforcement Learning: Acceleration, Convergence, and Stabilization
Ke Sun, Yafei Wang, Yi Liu, Yingnan Zhao, Bo Pan, SHANGLING JUI, Bei Jiang, Linglong Kong
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| Add stable regularization and MellowMax to DuelingDQN with Anderson acceleration | DuelingDQN · Breakout | average return: around 250 average return vs 150 return | Improved |
| Add stable regularization to DuelingDQN with Anderson acceleration (ablation) | DuelingDQN · SpaceInvaders | convergence | Improved |
| Add stable regularization to DuelingDQN with Anderson acceleration (ablation) | DuelingDQN · Enduro | sample efficiency | Mixed |
| Add MellowMax instead of the max operator (ablation) | DuelingDQN · SpaceInvaders | performance | No clear effect |
| Use MellowMax with inverse parameter ω=5.0 or 10.0 (ablation) | DuelingDQN · Enduro | final performance | Improved |
| Combine stable regularization with MellowMax (ablation) | DuelingDQN · SpaceInvaders and Enduro | sample efficiency | Improved |
Closest papers by meaning
- Stable Gradients for Stable Learning at Scale in Deep Reinforcement Learning (NeurIPS 2025 · similarity 0.86)
- Almost Sure Convergence Rates of Stochastic Approximation and Reinforcement Learning via a Poisson-Moreau Drift (NeurIPS 2026 · similarity 0.85)
- FASTER: Value-Guided Sampling for Fast RL (NeurIPS 2026 · similarity 0.85)
- Provable and Practical: Efficient Exploration in Reinforcement Learning via Langevin Monte Carlo (ICLR 2024 · similarity 0.85)
- Towards Global Optimality for Practical Average Reward Reinforcement Learning without Mixing Time Oracles (ICML 2024 · similarity 0.85)
- PRECISE: SDE-Consistent Stochastic Sampling for RL Post-Training of Flow-Matching Models (NeurIPS 2026 · similarity 0.85)
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.
