AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Effectively Learning Initiation Sets in Hierarchical Reinforcement Learning

Akhil Bagaria, Ben M Abbatematteo, Omer Gottesman, Matt Corsaro, Sreehari Rammohan, George Konidaris

NeurIPS 2023 · Reinforcement learning › Visual and representation RL · approach: Hierarchical skills and priors · 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
learn initiation sets with IVF or Weighted classifier instead of binary classifieroption initiation set learner · MiniGrid-FourRooms and Montezuma's Revengeinitiation set accuracy and sizeImproved
use binary classification over training time (baseline behavior)baseline binary classifier · FourRooms and Montezuma's Revengeinitiation set accuracy over timeHurt
add optimistic exploration bonus to IVF (ablation)IVF · Montezuma's Revengeinitiation set qualityImproved
add optimistic exploration bonus to IVF (ablation)IVF · MiniGrid-FourRoomsinitiation set qualityHurt
remove the optimistic count-based bonus (ablation)Weighted classifier · Robosuite SLIDEtask success rateHurt
use Weighted instead of Random/Binaryinitiation learner · Robosuite DOORtask success rateNo clear effect
use Weighted instead of IVF/Binary/Randominitiation learner · Robosuite LEVER and SLIDEtask success rate: above 50%Improved
add IVF or Weighted initiation learning to deep skill chainingDSC · Ant Medium-Mazesuccess rateImproved
use Weighted classifier instead of pure IVFDSC · Ant Medium-Mazemean return and varianceMixed

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