AI Paper Atlas

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

Matryoshka Policy Gradient for Entropy-Regularized RL: Convergence and Global Optimality

François G. Ged, Maria Han Veiga

JMLR 2024 · Reinforcement learning › Policy gradient and actor-critic · approach: Off-policy actor-critic with expressive policies · 0 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 MPG instead of PGREINFORCE · Frozen Lake (N=20)cumulative rewardNo clear effect
use MPG instead of softPG or nsPGpolicy gradient · Frozen Lake (N=20)cumulative rewardImproved
use MPG with shorter horizon N=10 or N=15 instead of PG, softPG, nsPGpolicy gradient · Frozen Lake (N=10, 15)treasure foundImproved
use MPG instead of PG/nsPGpolicy gradient · Cart Pole (N=100)test cumulative rewardNo clear effect
add entropy regularisation (MPG, softPG) vs PG (ablation)policy gradient · Cart Pole (N=100)episodes to reach same rewardHurt
use MPG instead of softPGpolicy gradient · Cart Pole (N=100)spread of test rewardImproved
use incomplete basis (4 of 5 features) in the analytical task (ablation)MPG · Analytical task (5 states, n=2)L-infinity error to optimal projected policyNo clear effect

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