AI Paper Atlas

Research map / Reinforcement learning / Policy gradient and actor-critic

Divergence-Augmented Policy Optimization

Qing Wang, Yingru Li, Jiechao Xiong, Tong Zhang

NeurIPS 2019 · Reinforcement learning › Policy gradient and actor-critic · approach: Trajectory reuse in policy gradients

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 KL divergence augmentation to the returnPPO · Atari Qbert (58-game suite)relative score improvement: +894%Improved
add KL divergence augmentation to the returnPPO · Atari VideoPinballrelative score improvement: +781%Improved
add KL divergence augmentation to the returnPPO · Atari Frostbiterelative score improvement: -19%Hurt
add KL divergence augmentation to the returnPPO · Atari 58 games, hard explorationrelative score improvementImproved
add KL divergence augmentation to the returnPPO · Atari Pong, Asterix, MontezumaRevengerelative score improvement: 1%, 0%No clear effect
replace divergence augmentation with entropy augmentation (ablation)PPO+DA · Atari selected gamesscoreHurt
tune entropy coefficient 1/eta over 0.5, 0.1, 0.01, 0.001 (ablation)PPO+Entropy · Atari selected gamesscore: best at 0.1Mixed
use 1-step divergence instead of multi-step discounted divergence (c_D = 0) (ablation)PPO+DA · Atari Enduro and QbertscoreHurt

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