AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

First-Order Representation Languages for Goal-Conditioned RL

Simon Ståhlberg, Hector Geffner

AAAI 2026 · Reinforcement learning › Visual and representation RL · approach: Graph search and compositional goals

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
relabel goals with propositional subsets instead of full statesR-GNN DQN · 15 planning domainscoverage: 51.0% -> 82.4%Improved
relabel goals with lifted subgoals instead of full statesR-GNN DQN · 15 planning domainscoverage: 51.0% -> 78.6%Improved
lift propositional HER subgoalsR-GNN DQN · 15 planning domainscoverage: 82.4% -> 78.6%Mixed
use lifted HER instead of propositionalR-GNN DQN · Mazecoverage: 0 relabeled -> 100% coverageImproved
use lifted HER instead of state HERR-GNN DQN · Miconic-Linstances solved: 0 -> 100Improved
use lifted HER instead of propositional HERR-GNN DQN · Childsnackinstances solved: 100 -> 56Hurt
use any HER variantR-GNN DQN · Hikinginstances solved: 0 -> 0No clear effect
use any HER variant on DeliveryR-GNN DQN · Deliveryinstances solved: State 0; lifted 12; propositional 11Hurt
use learned greedy policy instead of LAMAR-GNN DQN propositional HER · 15 planning domainscoverage: 80.8% -> 82.4%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