AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

LTL2Action: Generalizing LTL Instructions for Multi-Task RL

Pashootan Vaezipoor, Andrew C Li, Rodrigo A Toro Icarte, Sheila A. Mcilraith

ICML 2021 · Reinforcement learning › Visual and representation RL · approach: Probabilistic and autonomous 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
Use LTL progression rather than processing the unprogressed instruction with a recurrent policyLTL2Action · Avoidance Tasks, increased depthtotal reward: -0.03 -> 0.98Improved
Use LTL progression rather than processing the unprogressed instruction with a recurrent policyLTL2Action · Partially-Ordered Tasks, increased depthtotal reward: 0.03 -> 0.97Improved
Use a GNN formula encoder instead of a GRU formula encoder (ablation)LTL2Action with progression · Avoidance Tasks, increased depthtotal reward: 0.42 -> 0.98Improved
Use a GNN formula encoder instead of a GRU formula encoder (ablation)LTL2Action with progression · Partially-Ordered Tasks, increased depthtotal reward: 0.29 -> 0.97Improved
Pretrain the LTL module before downstream training (ablation)LTL2Action with GNN encoder · LetterWorldsample efficiencyImproved
Encode and optimize the full LTL task rather than selecting only the next proposition myopicallyLTL2Action · Avoidance Tasks, IIDtotal reward: 0.88 -> 0.98Mixed
Replace one-hot proposition features with fixed low-dimensional vectors (ablation)LTL2Action · LetterWorld, tasks with unseen lettersmean return: $-0.374 \pm 0.021$ -> $0.667 \pm 0.015$Improved
Use a GRU rather than a GNN to encode formulas (ablation)LTL2Action · LetterWorldwall-clock efficiency: 2-3$\times$Improved

Later papers that compared with this method

2 later accepted papers report LTL2Action as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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