AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Action Schema Networks: Generalised Policies With Deep Learning

Sam Toyer, Felipe Trevizan, Sylvie Thiébaux, Lexing Xie

AAAI 2018 · Reinforcement learning › Visual and representation RL · approach: RL for combinatorial routing · 69 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 LM-cut landmark features as network inputs (ablation)ASNet · Probabilistic Blocks World, extended tests with 10–35 blockscoverageImproved
Use LM-cut landmark features as network inputs (ablation)ASNet · CosaNostra Pizza test setcoverageImproved
Omit LM-cut input features (ablation)ASNet (h-add) · Triangle Tire World, sizes 15 and 20solution time: 2.4x; 4.3xImproved
Train with potentially suboptimal h-add teacher policies instead of optimal policies (ablation)ASNet · Probabilistic Blocks Worldability to converge within the training time limitImproved
Increase network depth to provide enough layers to see the hazard (ablation)ASNet · Monster, path length 5coverage: 14/30 -> 30/30Improved
Increase network depth to provide enough layers to see the hazard (ablation)ASNet · Monster, path length 4coverage: 14/30 -> 30/30Improved
Omit LM-cut input features (ablation)ASNet (h-add) · Probabilistic Blocks World, problems up to 20 blockssolution cost: 65.93 ± 2.39 vs 70.33 ± 2.51; 69.53 ± 2.81 vs 77.30 ± 2.60Mixed

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