AI Paper Atlas

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

Hierarchical Relative Entropy Policy Search

Christian Daniel, Gerhard Neumann, Oliver Kroemer, Jan Peters

JMLR 2016 · Reinforcement learning › Policy gradient and actor-critic · approach: Model-based RL with guarantees · 166 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 hierarchical sub-policies (HiREPS) instead of a single sub-policy (REPS)REPS · tetherball with states, simulationaverage rewardImproved
bound the overlap of sub-policies (ablation)HiREPS · tetherball with states, simulationaverage rewardImproved
bound the overlap of sub-policies (ablation)HiREPS · tetherballnumber of sub-policies usedImproved
bound the overlap of sub-policies (ablation)HiREPS · tetherballnumber of modes foundImproved
use HiREPS instead of REPSREPS · tetherball without stateslearning speedImproved
use HiREPS instead of REPS on puddle worldREPS · puddle worldaverage rewardImproved
learn skill sequencing with HiREPS on the physical tetherball simulationHiREPS · tetherball winding simulationsuccessful trials: 5/5 trialsImproved

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