AI Paper Atlas

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

An operator view of policy gradient methods

Dibya Ghosh, Marlos C. Machado, Nicolas Le Roux

NeurIPS 2020 · Reinforcement learning › Policy gradient and actor-critic · approach: Trajectory reuse in policy gradients · 8 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
Pair polynomial-return improvement with KL projection instead of the matching α-divergence projection (ablation)Op-Reinforce with polynomial returns · Four-room domainlearning speedImproved
Pair polynomial-return improvement with KL projection (ablation)Op-Reinforce with polynomial returns · Four-room domainconvergence qualityHurt
Use the corresponding α-divergence projection with polynomial-return improvement (ablation)Op-Reinforce with polynomial returns · Four-room domainlearning speedImproved
Use the corresponding α-divergence projection with polynomial-return improvement (ablation)Op-Reinforce with polynomial returns · Four-room domainconvergence qualityImproved
Anneal α to 1 during optimization while using polynomial-return improvement (ablation)Op-Reinforce with polynomial returns · Four-room domainlearning speedImproved
Anneal α to 1 during optimization while using polynomial-return improvement (ablation)Op-Reinforce with polynomial returns · Four-room domainconvergence qualityImproved
Increase return variance with entropy regularizationPolicy-gradient methods · Policy-gradient learningimprovement per updateImproved
Use an almost-deterministic policy in a deterministic environmentPolicy-gradient methods · Deterministic policy and environmentlearning progressHurt

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