Research map / Reinforcement learning / Visual and representation RL
Guiding Search in Continuous State-Action Spaces by Learning an Action Sampler From Off-Target Search Experience
Beomjoon Kim, Leslie Kaelbling, Tomás Lozano-Pérez
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 |
|---|---|---|---|
| learn action sampler with GANDI instead of uniform sampling | heuristic-forward search · Bin packing | success rate within 5 s: about 50% -> more than 70% | Improved |
| add off-target samples via importance-ratio estimation (GANDI vs standard GAN) (ablation) | GAN action sampler · Bin packing | training episodes needed to beat uniform: 50 -> 20 episodes | Improved |
| learned samplers (GAN, GANDI) instead of uniform sampling | heuristic-forward search · Stow | success rate within 30 s | Improved |
| add off-target samples (GANDI vs GAN) (ablation) | GAN action sampler · Stow | success rate | Improved |
| add off-target samples (GANDI vs GAN) (ablation) | GAN action sampler · Reconfiguration | success rate within 10 s | Mixed |
Closest papers by meaning
- Graph Sparse Sampling: Breaking the Curse of the Horizon in Continuous MDP Planning (NeurIPS 2026 · similarity 0.86)
- Generative Trajectory Stitching through Diffusion Composition (NeurIPS 2025 · similarity 0.86)
- Efficient Robotic Policy Learning via Latent Space Backward Planning (ICML 2025 · similarity 0.86)
- GenPlan: Generative Sequence Models as Adaptive Planners (AAAI 2025 · similarity 0.86)
- Generative Control as Optimization: Time Unconditional Flow Matching for Adaptive and Robust Robotic Control (NeurIPS 2026 · similarity 0.86)
- Differentiable Learning of Lifted Action Schemas for Classical Planning (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.
