Research map / Reinforcement learning / Visual and representation RL
Sparse Latent Space Policy Search
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| GrouPS with 1 group spanning all joints instead of PePPEr | GrouPS · Bi-manual 12-DoF planar reaching | summed end-effector distance | Hurt |
| split joints into 2 groups (one per arm) instead of 1 group (ablation) | GrouPS · Bi-manual 12-DoF planar reaching | summed end-effector distance | Helped |
| use 4 groups instead of 1 or 2 groups (ablation) | GrouPS · Bi-manual 12-DoF planar reaching | summed end-effector distance | Helped |
| GrouPS (4 groups) instead of PoWER and NAC | GrouPS · Bi-manual 12-DoF planar reaching | summed end-effector distance | Helped |
| randomly swap joints between groups (two or three swaps) (ablation) | GrouPS 4 groups · Bi-manual 12-DoF planar reaching | summed end-effector distance | Hurt |
| use different splitting points for groups (2/4, 6 groups, 3/3 split) (ablation) | GrouPS 4 groups · Bi-manual 12-DoF planar reaching | summed end-effector distance | Hurt |
Closest papers by meaning
- Learning an Embedding Space for Transferable Robot Skills (ICLR 2018 · similarity 0.90)
- Learning transferable motor skills with hierarchical latent mixture policies (ICLR 2022 · similarity 0.89)
- High-Dimensional Robotic Reinforcement Learning with Developing Synergies (NeurIPS 2026 · similarity 0.89)
- Latent Policy Barrier: Learning Robust Visuomotor Policies by Staying In-Distribution (NeurIPS 2025 · similarity 0.86)
- Foundation Policies with Hilbert Representations (ICML 2024 · similarity 0.86)
- Efficient Planning with Latent Diffusion (ICLR 2024 · 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.