AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Learning Space Partitions for Path Planning

Kevin Yang, Tianjun Zhang, Chris Cummins, Brandon Cui, Benoit Steiner, Linnan Wang, Joseph E. Gonzalez, Dan Klein, Yuandong Tian

NeurIPS 2021 · Reinforcement learning › Visual and representation RL · approach: RL for combinatorial routing · 2 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 reward-informed learned partitions and latent-space planningLaP^3 · MiniWorld MazeS3success percentage: LaP^3: 57.0 $\pm$ 3.1; VOOT: 26.2 $\pm$ 2.7Improved
Use reward-informed learned partitions and latent-space planningLaP^3 · MiniWorld FourRoomssuccess percentage: LaP^3: 89.1 $\pm$ 2.0; CMA-ES: 79.7 $\pm$ 2.5Improved
Use reward-informed learned partitions and latent-space planningLaP^3 · MiniWorld SelectObjsuccess percentage: LaP^3: 45.3 $\pm$ 3.1; PPO: 31.3 $\pm$ 8.2Improved
Replace the PETS CEM planner with LaP^3PETS · MiniWorld FourRoomsfraction of environment seeds solved: 66.9 $\pm$ 6.3 -> 83.1 $\pm$ 2.3Improved
Replace the PETS CEM planner with LaP^3PETS · MiniWorld SelectObjfraction of environment seeds solved: 7.2 $\pm$ 1.9 -> 19.4 $\pm$ 1.8Improved
Use reward-informed learned partitions and latent-space planningLaP^3 · MiniGrid MR-N4S5reward: -14.31$\pm$0.78 -> -11.68$\pm$0.75Improved
Use reward-informed learned partitions and latent-space planningLaP^3 · Molecular design DRD2max property value: 0.323 $\pm$ 0.016 -> 0.648 $\pm$ 0.026Improved
Use mean rather than maximum node value (ablation)LaP^3 · MiniWorld MazeS3success percentage: 57.0 $\pm$ 3.1 -> 43.4 $\pm$ 3.1Hurt
Remove latent partition space (ablation)LaP^3 · MiniWorld MazeS3success percentage: 57.0 $\pm$ 3.1 -> 26.6 $\pm$ 2.8Hurt
Remove tree traversal and directly select the highest-UCB leaf (ablation)LaP^3 · MiniWorld MazeS3success percentage: 57.0 $\pm$ 3.1 -> 24.6 $\pm$ 2.7Hurt
Remove the UCB exploration bonus (ablation)LaP^3 · MiniWorld MazeS3success percentage: 57.0 $\pm$ 3.1 -> 28.1 $\pm$ 2.8Hurt
Use data-driven reward-sensitive partitioning instead of random partitioningLaP^3 · MiniWorldestimated average Lipschitz constant and c_kImproved

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