Research map / Reinforcement learning / MDPs and planning
Sample-Efficient Iterative Lower Bound Optimization of Deep Reactive Policies for Planning in Continuous MDPs
Siow Meng Low, Akshat Kumar, Scott Sanner
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 ILBO instead of TFMDP | Deep reactive policy planning · Navigation | sample efficiency | Improved |
| Use ILBO instead of TFMDP | Deep reactive policy planning · HVAC | solution quality | Improved |
| Use ILBO instead of TFMDP | Deep reactive policy planning · Reservoir-20 | training stability | Improved |
| Use the ILBO policy without retraining instead of retraining TFMDP | Deep reactive policy planning · HVAC-6 new initial states | total cost | Improved |
| Use the ILBO policy without retraining instead of retraining TFMDP | Deep reactive policy planning · Reservoir-20 new initial states | total cost | Mixed |
Closest papers by meaning
- Diffusion Policy Policy Optimization (ICLR 2025 · similarity 0.87)
- Deterministic Policy Gradient Primal-Dual Methods for Continuous-Space Constrained MDPs (AAAI 2025 · similarity 0.86)
- Confident Natural Policy Gradient for Local Planning in $q_\pi$-realizable Constrained MDPs (NeurIPS 2024 · similarity 0.86)
- Near-Optimal Sample Complexity for Online Constrained MDPs (NeurIPS 2025 · similarity 0.85)
- Beyond Stationarity: Convergence Analysis of Stochastic Softmax Policy Gradient Methods (ICLR 2024 · similarity 0.85)
- DiRecT: Safe Diffusion-Based Planning via Receding-Horizon Denoising (NeurIPS 2026 · 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.
