AI Paper Atlas

Research map / Reinforcement learning / MDPs and planning

Data-Efficient Reinforcement Learning in Continuous State-Action Gaussian-POMDPs

Rowan McAllister, Carl Edward Rasmussen

NeurIPS 2017 · Reinforcement learning › MDPs and planning · approach: POMDP policy optimization · 19 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
Plan in belief space with filtered multi-step prediction and filtered executionPILCO · Cartpole swing-up, common datasetempirical cost: min z = 3.51Improved
Filter only during execution (Deisenroth and Peters) vs no filtering (ablation)PILCO · Cartpole swing-up, common datasetempirical costImproved
Add filtered multi-step prediction on top of filtered execution (ablation)Deisenroth and Peters · Cartpole swing-up, common datasetempirical cost: gain -39.1 -> -81.7 N/radImproved
Use MAP-trajectory prediction ignoring model uncertainty (Dallaire) (ablation)filtered PILCO · Cartpole swing-up, common datasetpredicted vs empirical costHurt
Let each algorithm collect its own data (15 trials, 10 seeds)Filtered PILCO · Cartpole swing-up full RLempirical lossImproved
Dallaire method with self-collected dataDallaire et al. · Cartpole swing-up full RLpredicted lossHurt
Increase observation noise factor k from 1unfiltered PILCO · Cartpole swing-up noise sweepempirical lossHurt
Low noise factor k = 1, filtering vs none (ablation)Filtered PILCO · Cartpole swing-up noise sweepempirical lossNo clear effect
Increase observation noise factor kFiltered PILCO · Cartpole swing-up noise sweepempirical lossNo 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