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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Represent actions and state using deictic image crops centered and aligned on the target pose | DQN on grid-disk · 5 × 5 grid-disk | learning speed | Improved |
| Use deictic image mapping with an eight-stage curriculum | DQN for block alignment · Simulated block alignment | average reward per episode | Improved |
| Remove curriculum stages 1–3 before training stage 4 (ablation) | Deictic image mapping · Block alignment, curriculum stage 4 | learning speed | No clear effect |
| Remove curriculum stages 1–4 before training stage 5 (ablation) | Deictic image mapping · Block alignment, curriculum stage 5 | task learning | Hurt |
| Add the value function hierarchy (ablation) | Deictic image mapping · Block alignment, first six curriculum stages | average reward per episode: approximately 15% worse | Hurt |
Closest papers by meaning
- Implicit Drifting Policy: One-Step Action Generation via Conditional Expert Geometry (NeurIPS 2026 · similarity 0.86)
- Zero-Shot Robotic Manipulation with Pre-Trained Image-Editing Diffusion Models (ICLR 2024 · similarity 0.86)
- GravMAD: Grounded Spatial Value Maps Guided Action Diffusion for Generalized 3D Manipulation (ICLR 2025 · similarity 0.86)
- Multi-Stage Manipulation with Demonstration-Augmented Reward, Policy, and World Model Learning (ICML 2025 · similarity 0.86)
- DeformGen: Dynamics-Based Topology Augmentation for Deformable Manipulation Policy Learning (NeurIPS 2026 · similarity 0.85)
- Prediction with Action: Visual Policy Learning via Joint Denoising Process (NeurIPS 2024 · similarity 0.85)
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.
