AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Successor Feature Landmarks for Long-Horizon Goal-Conditioned Reinforcement Learning

Christopher Hoang, Sungryull Sohn, Jongwook Choi, Wilka Torrico Carvalho, Honglak Lee

NeurIPS 2021 · Reinforcement learning › Visual and representation RL · approach: Graph search and compositional goals · 3 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 SFS instead of SPTM's reachability network as the distance metric (ablation)SFL · ViZDoom SGM-Map, random spawnsuccess rate: 83 ± 1.2% -> 92 ± 1.7%; 57 ± 2.6% -> 82 ± 0.6%; 24 ± 1.9% -> 67 ± 2.6%Improved
Sample frontier landmarks by inverse visitation count instead of uniformly at random (ablation)SFL · ViZDoom Test-1state coverage: 72.3 ± 1.90% -> 79.4 ± 0.65%Improved
Build landmarks progressively and retain landmark metadata instead of using clustering (ablation)SFL · Three-room MultiRoomsuccess rate: 35.6 ± 18.8% -> 75.0 ± 14.6%Improved
Build landmarks progressively rather than with clustering (ablation)SFL · FourRoomaverage pairwise geodesic distance between landmarks: 5.72 ± 0.40 -> 6.72 ± 0.43Improved
Use SFL rather than the strongest reported baselineLong-horizon goal-reaching · ViZDoom random spawn, hard taskssuccess rate: SGM-Map: 26% -> 67%; Test-2: 32% -> 48%; Test-6: 27% -> 60%Improved
Use SFL rather than the strongest reported baselineExploration and goal-reaching · ViZDoom fixed spawnsuccess rate: Test-1 Hard: 1% -> 62%; Test-1 Hardest: 1% -> 50%; Test-4 Hard: 7% -> 27%; Test-4 Hardest: 7% -> 23%Improved

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