AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Landmark-Guided Subgoal Generation in Hierarchical Reinforcement Learning

Junsu Kim, Younggyo Seo, Jinwoo Shin

NeurIPS 2021 · Reinforcement learning › Visual and representation RL · approach: Subgoal generation for hierarchical RL · 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
Guide high-level subgoals toward landmarks sampled for coverage and noveltyHIGL versus HRAC · Ant Maze (U-shape, sparse), 10 × 10^5 timestepssuccess rate: 17.6% -> 65.1%Improved
Add coverage-based landmarks (ablation)HIGL · Ant Maze (U-shape, dense)performanceImproved
Add novelty-based landmarks (ablation)HIGL with coverage-based sampling · Ant Maze (U-shape, dense)performanceImproved
Use pseudo-landmarks instead of raw selected landmarks (ablation)HIGL · Ant Maze (W-shape, dense)performanceImproved
Increase the number of landmarks (ablation)HIGL · Ant Maze (U-shape, dense)performanceImproved
Set pseudo-landmark shift magnitude too small (ablation)HIGL · Ant Maze (U-shape, dense)performanceHurt
Set pseudo-landmark shift magnitude to 4 (ablation)HIGL · Ant Maze (U-shape, dense)performanceHurt
Set adjacency degree too large (k=20) (ablation)HIGL · Ant Maze (U-shape, dense)performanceHurt
Use shortest-transition-distance-based queue discarding instead of L2-distance-based discarding (ablation)HIGL novelty priority queue · Additional experimentsperformanceMixed
Set shift magnitude automatically from average selected-landmark distance (ablation)HIGL · Additional experimentsperformanceImproved
Use HIGL rather than HRACAnt Maze (U-shape), 24 × 24, extended timestep · Ant Maze (U-shape), 24 × 24training time: 6 hours -> 13 hoursHurt

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