AI Paper Atlas

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

A Family of Robust Stochastic Operators for Reinforcement Learning

Yingdong Lu, Mark Squillante, Chai Wah Wu

NeurIPS 2019 · Reinforcement learning › Policy gradient and actor-critic · approach: Model-based RL with guarantees · 2 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
Replace the Bellman operator with RSO using βₖ ~ U[0,2)Q-learning · Acrobotmean action gap: 0.1436 -> 0.9004Improved
Replace the Bellman operator with RSO using βₖ ~ U[0,2)Q-learning · Mountain Car testaverage score: 129.93 -> 122.70Improved
Replace the Bellman operator with RSO using βₖ ~ U[0,2)Q-learning · Mountain Car testscore standard deviation: 32.68 -> 7.25Improved
Replace the Bellman operator with RSO using βₖ ~ U[0,2)Q-learning · Cart Pole, last 100 episodesaverage score: 183.67 -> 190.92Improved
Replace the Consistent Bellman operator with RSO using βₖ ~ U[0,2)Q-learning · Cart Pole, last 100 episodesaverage score: 184.07 -> 190.92Improved
Replace the Bellman operator with RSO using βₖ ~ U[0,2)Q-learning · Cart Polescore standard deviation: 28.87 -> 19.44Improved
Replace the Bellman operator with RSO using βₖ ~ U[0,2)Q-learning · Lunar Lander testaverage score: -241.94 -> -167.51Improved
Use βₖ ~ U[0,1) instead of βₖ ~ U[0,2) (ablation)RSO · OpenAI Gym problemsperformanceHurt
Fix βₖ = 1 instead of sampling βₖ ~ U[0,2) (ablation)RSO · OpenAI Gym problemsperformanceHurt
Use mixtures of β distributions across iterations rather than βₖ ~ U[0,2) throughout (ablation)RSO · OpenAI Gym problemsperformanceHurt
Increase variability in the βₖ sequence while preserving its meanRobust stochastic operators · Theoretical action-gap resultaction gapImproved

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