AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

EAGER: Asking and Answering Questions for Automatic Reward Shaping in Language-guided RL

Thomas Carta, Pierre-Yves Oudeyer, Olivier Sigaud, sylvain lamprier

NeurIPS 2022 · Reinforcement learning › Visual and representation RL · approach: Graph search and compositional goals · 5 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 EAGER question-generation and question-answering reward shapingPPO · Unlock-Mediumaverage reward: 0.8903 vs 0.8765Improved
Use EAGER question-generation and question-answering reward shapingPPO · PutNextTo and Sequence tasksperformanceImproved
Use EAGER question-generation and question-answering reward shapingPPO · Unlock tasksperformanceImproved
Combine EAGER reward shaping with RIDEEAGER · Unlock-Mediumaverage rewardImproved
Combine EAGER reward shaping with RIDEEAGER · PutNext-local and PutNext-mediumaverage rewardHurt
Train QA on a wide distribution of successful trajectories rather than a narrow distribution (ablation)EAGER · BabyAI taskssample efficiencyImproved
Add a no_answer response to the QA (ablation)EAGER · PutNextTosample efficiencyImproved
Reward answers by confidence instead of using a binary reward (ablation)EAGER · PutNextTosample efficiencyImproved
Remove neutralization of intrinsic reward on successful trajectories (ablation)EAGER · PutNextTo-Localfinal performanceHurt
Use QA trained on unseen rather than seen goalsEAGER QA · Sequence-MediumQA success rate: 0.74 -> 0.67Hurt
Use the QA training dataset to train an agent with behavioural cloningBehavioural cloning · PutNextTo-Localsuccess rate: 0Hurt
Use the QA training dataset with IQLIQL · PutNextTo-Localsuccess rate: 0Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

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