AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Deictic Image Mapping: An Abstraction for Learning Pose Invariant Manipulation Policies

Robert Platt, Colin Kohler, Marcus Gualtieri

AAAI 2019 · Reinforcement learning › Visual and representation RL · approach: Vision-based robot RL · 11 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
Represent actions and state using deictic image crops centered and aligned on the target poseDQN on grid-disk · 5 × 5 grid-disklearning speedImproved
Use deictic image mapping with an eight-stage curriculumDQN for block alignment · Simulated block alignmentaverage reward per episodeImproved
Remove curriculum stages 1–3 before training stage 4 (ablation)Deictic image mapping · Block alignment, curriculum stage 4learning speedNo clear effect
Remove curriculum stages 1–4 before training stage 5 (ablation)Deictic image mapping · Block alignment, curriculum stage 5task learningHurt
Add the value function hierarchy (ablation)Deictic image mapping · Block alignment, first six curriculum stagesaverage reward per episode: approximately 15% worseHurt

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