AI Paper Atlas

Research map / Reinforcement learning / MDPs and planning

Non-parametric Policy Search with Limited Information Loss

Herke van Hoof, Gerhard Neumann, Jan Peters

JMLR 2017 · Reinforcement learning › MDPs and planning · approach: Average-reward and regularized MDPs · 23 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 KL bound epsilon 0.5 rather than epsilon 5 in NP-REPS (ablation)NP-REPS with model · Low-dimensional swing-upaverage reward learning curve: epsilon = 5 vs epsilon = 0.5Improved
use KL bound epsilon 0.5 rather than epsilon 0.05 (ablation)NP-REPS with model · Low-dimensional swing-uplearning speed: epsilon = 0.05 vs epsilon = 0.5Improved
model transitions with learned model instead of sample-based (ablation)NP-REPS · Low-dimensional swing-up (stochastic)average rewardImproved
learned model instead of sample-based transitions (ablation)NP-REPS · Reaching task (deterministic)learning speedHurt
use non-parametric representation instead of fixed features (ablation)REPS · Low-dimensional swing-upaverage reward in later iterationsImproved
use Fourier features with 500 bases instead of sub-sampling (ablation)kernel approximation · Swing-up approximation (500 bases)average reward: sampled subset performs very badly at 500 basesImproved
use regression-based sparsification instead of Fourier features (ablation)kernel approximation · Swing-up approximation (100 bases)learning speed: about 7% of training dataImproved
use Fourier approximation with 500 bases instead of exact kernel (ablation)NP-REPS · Swing-up approximationcomputation time: about twice as fast at a similar level of performanceImproved
use NP-REPS instead of on-policy value iterationpolicy update · Low-dimensional swing-upaverage rewardImproved
use NP-REPS instead of DDPGimage-based policy search · Image-based puddle worldreturnImproved
use joint values instead of camera image representationNP-REPS · Real-robot swing-uplearning performanceImproved

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