AI Paper Atlas

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

Policy Optimization by Genetic Distillation

Tanmay Gangwani, Jian Peng

ICLR 2018 · Reinforcement learning › Policy gradient and actor-critic · approach: Alternative policy update rules · 11 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
Use state-space imitation-learning crossover instead of parameter-space crossoverGPO policies · HalfCheetahaverage episode rewardImproved
Add data-sharing during policy-gradient mutation (ablation)Base policy-optimization procedure · Ant and Walker-2D (normalized average)normalized performance: 0.33 -> 0.83Improved
Add state-space imitation-learning crossover (ablation)Base policy-optimization procedure · Ant and Walker-2D (normalized average)normalized performance: 0.33 -> 0.47Improved
Use performance-fitness selection rather than random selection (ablation)Base policy-optimization procedure · Ant and Walker-2D (normalized average)normalized performance: 0.33 -> 0.47Improved
Combine data-sharing with performance-based parent selection (ablation)Base policy-optimization procedure · Ant and Walker-2D (normalized average)normalized performance: 0.83 -> 0.86Improved
Use GPO rather than the strongest policy-gradient baselinePPO policy optimization · MuJoCo locomotion tasksfinal mean episode rewardMixed
Use GPO rather than the strongest policy-gradient baselineA2C policy optimization · MuJoCo locomotion tasksfinal mean episode rewardMixed
Increase GPO population sizeGPO · Walker2DperformanceImproved

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