Research map / Reinforcement learning / Visual and representation RL
Representation Learning for Event-based Visuomotor Policies
Sai Vemprala, Sami Mian, Ashish Kapoor
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 |
|---|---|---|---|
| Use BRP-full instead of normal-frame input | Visuomotor policy · Test track | success (%): 40% -> 98% | Improved |
| Use BRP-full instead of event-frame input | Visuomotor policy · Test track | success (%): 89% -> 98% | Improved |
| Use event-frame input instead of normal-frame input | Visuomotor policy · Test track | success (%): 40% -> 89% | Improved |
| Include polarity and timestamp information, as in BRP-full rather than BRPxy (ablation) | BRP representation for navigation · Presented navigation task | navigation performance | Improved |
| Use an event-based representation rather than normal-frame input | Visuomotor policy · Intra-task generalization | generalization | Improved |
| Use the event-based method at faster control rates with sparse data | Visuomotor policy · Sparse-data control | control performance | Improved |
Closest papers by meaning
- E-Motion: Future Motion Simulation via Event Sequence Diffusion (NeurIPS 2024 · similarity 0.87)
- Leveraging Asynchronous Spiking Neural Networks for Ultra Efficient Event-Based Visual Processing (AAAI 2025 · similarity 0.87)
- DynaMo: In-Domain Dynamics Pretraining for Visuo-Motor Control (NeurIPS 2024 · similarity 0.87)
- Towards Principled Representation Learning from Videos for Reinforcement Learning (ICLR 2024 · similarity 0.86)
- PASS: Path-selective State Space Model for Event-based Recognition (NeurIPS 2025 · similarity 0.86)
- Event-Grounded Sparse Autoencoders for Vision-Language-Action Policies (NeurIPS 2026 · similarity 0.86)
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.
