atlas

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

Greedy Actor-Critic: A New Conditional Cross-Entropy Method for Policy Improvement

ICLR 2023 · Reinforcement learning › Policy gradient and actor-critic · approach: Actor-critic theory

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 Boltzmann (SAC-style) actor update with percentile-greedy CCEM actor update (GreedyAC)actor-critic · continuous-action classic control (across-environment tuning)aggregate normalized returnHelped
Replace Boltzmann actor update with CCEM actor updateactor-critic · continuous-action environments (entropy sensitivity)sensitivity to entropy scaleHelped
Replace Boltzmann actor update with CCEM actor updateactor-critic · Pendulum-CA (per-environment tuning)final returnHurt
Replace Boltzmann actor update with CCEM actor updateactor-critic · Mountain Car (per-environment tuning)final returnHelped
Replace Boltzmann actor update with CCEM actor updateactor-critic · Acrobot (per-environment tuning)learning speedHelped

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