AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Temporally Abstract Partial Models

Khimya Khetarpal, Zafarali Ahmed, Gheorghe Comanici, Doina Precup

NeurIPS 2021 · Reinforcement learning › Visual and representation RL · approach: Inferring decision-making from behavior · 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
collect data and mask model-learning loss with the Pickup+Drop@Goal affordance set instead of all options (ablation)partial option model learning · Taxisuccess rate / sample efficiency: 37,500 -> 4,000 state-option pairsImproved
Pickup+Drop (25,000 pairs) instead of Everything (37,500 pairs) during model learning (ablation)partial option model learning · Taxisample efficiency: 37,500 -> 25,000No clear effect
use any affordance set during model learning allows a higher learning rate (ablation)partial option model learning · Taxitraining stability (divergence at high learning rate)Improved
apply affordance sets only during planning with the same learned model (ablation)value iteration over options · Taxisuccess rateNo clear effect
use the restrictive affordance set in both model learning and planning (ablation)partial option model · Taxisample efficiencyImproved
learn affordances online with a classifier instead of hand-designed Pickup+Drop@Goalpartial option model · Taxiaffordance set size and sample efficiency: 4,000 -> 2,000Improved
increase affordance threshold k so the affordance set shrinks (ablation)learned affordance classifier · Taxisample efficiencyImproved
threshold k = 0 (all state-options affordable) (ablation)learned affordance classifier · Taxiaffordance set sizeNo 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