AI Paper Atlas

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

NeurIPS 2021 · Reinforcement learning › Policy gradient and actor-critic · approach: Regularized scalable deep value learning · 1 citations (OpenAlex)

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 changedWhereMeasuredEffect
Add stable regularization and MellowMax to DuelingDQN with Anderson accelerationDuelingDQN · Breakoutaverage return: around 250 average return vs 150 returnImproved
Add stable regularization to DuelingDQN with Anderson acceleration (ablation)DuelingDQN · SpaceInvadersconvergenceImproved
Add stable regularization to DuelingDQN with Anderson acceleration (ablation)DuelingDQN · Endurosample efficiencyMixed
Add MellowMax instead of the max operator (ablation)DuelingDQN · SpaceInvadersperformanceNo clear effect
Use MellowMax with inverse parameter ω=5.0 or 10.0 (ablation)DuelingDQN · Endurofinal performanceImproved
Combine stable regularization with MellowMax (ablation)DuelingDQN · SpaceInvaders and Endurosample efficiencyImproved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy