AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Natural Language Instruction-following with Task-related Language Development and Translation

Jing-Cheng Pang, Xinyu Yang, Si-Hang Yang, Xiong-Hui Chen, Yang Yu

NeurIPS 2023 · Reinforcement learning › Visual and representation RL · approach: Graph search and compositional goals · 0 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
Replace natural-language policy input (outside-in learning) with learned task language TL (inside-out learning)instruction-following policy · FrankaKitchensuccess rate improvement (%): 63.2%Improved
Replace natural-language policy input with learned task language TLinstruction-following policy · CLEVR-Robotsuccess rate improvement (%): 13.4%Improved
Increase number of NL sentence patterns from 1 to 9 for TALARTALAR · CLEVR-Robot trainsuccess rate (%): 100% -> 99.9%No clear effect
Increase number of NL sentence patterns from 1 to 9 for One-hot baselineOne-hot · CLEVR-Robot trainsuccess rate (%): 98.2% -> 86.5%Hurt
Increase number of NL sentence patterns from 1 to 9 for BERT-binary baselineBERT-binary · CLEVR-Robot trainsuccess rate (%): 82.0% -> 64.0%Hurt
Increase number of NL sentence patterns from 1 to 9 for BERT-continuous baselineBERT-continuous · CLEVR-Robot trainsuccess rate (%): 95.3% -> 60.7%Hurt
Use TL instead of NL as high-level goal abstraction in hierarchical RL (vs HAL)high-level policy · CLEVR-Robot and FrankaKitchen long-horizon taskssample efficiency (episodic reward)Improved
Increase number of predicate networks Npn (2, 4, 6) and argument count Na (2, 3, 4) (ablation)TALAR translator · FrankaKitchen (4M steps)success rate (train/test)Improved
Excessively large Npn and Na (ablation)TALAR translator · FrankaKitchentraining efficiencyHurt
Fine-tune BERT encoder on the task in OIL baselineBERT-based baseline · FrankaKitchen t-SNE of NL encodingsuniqueness of encodingNo clear effect

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