AI Paper Atlas

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

Diverse Exploration via Conjugate Policies for Policy Gradient Methods

Andrew Cohen, Xingye Qiao, Lei Yu, Elliot Way, Xiangrong Tong

AAAI 2019 · Reinforcement learning › Policy gradient and actor-critic · approach: Variance-reduced policy gradients · 6 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 conjugate perturbations rather than random perturbationsTRPO · Hoppertotal pairwise KL divergence: 53.5 vs. 38.1Improved
Use conjugate perturbations rather than random perturbationsTRPO · Walkertotal pairwise KL divergence: 82.7 vs. 77.6Improved
Use conjugate perturbations rather than random perturbationsTRPO · HalfCheetahtotal pairwise KL divergence: 192.5 vs. 156.1Improved
Use conjugate perturbations rather than random perturbationsTRPO · Hopperaverage performance of all behavior policiesImproved
Use conjugate perturbations rather than random perturbationsTRPO · Walkeraverage performance of all behavior policiesImproved
Use conjugate perturbations rather than random perturbationsTRPO · HalfCheetahaverage performance of all behavior policiesImproved
Increase the number of perturbed policies (ablation)DE on TRPO · Hopperaverage performanceImproved
Increase the number of perturbed policies (ablation)DE on TRPO · Hopperperformance varianceImproved

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