Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
Robust $\phi$-Divergence MDPs
Chin Pang Ho, Marek Petrik, Wolfram Wiesemann
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 the tailored KL-divergence projection algorithm instead of MOSEK | KL projection problem · KL projection problem, S=3,000 | runtime (ms): 139.13 -> 0.58 | Improved |
| Use the tailored KL robust Bellman update instead of MOSEK | KL robust Bellman update · KL Bellman update, S = A = 300 | runtime (ms): 215,871.00 -> 176.35 | Improved |
| Use the tailored KL robust Bellman update instead of the first-order method after 3 iterations | KL robust Bellman update · KL Bellman update, S = A = 300 | runtime (ms): 1,542.03 -> 176.36 | Improved |
| Use the tailored KL robust Bellman update instead of the first-order method after 5 iterations | KL robust Bellman update · KL Bellman update, S = A = 300 | runtime (ms): 4,283.27 -> 176.36 | Improved |
| Use the tailored chi-square projection algorithm instead of MOSEK | chi-square projection problem · chi-square projection problem, S=3,000 | runtime (ms): 153.06 -> 0.17 | Improved |
| Use the tailored chi-square robust Bellman update instead of MOSEK | chi-square robust Bellman update · chi-square Bellman update, S = A = 300 | runtime (ms): 1,908.92 -> 25.84 | Improved |
Closest papers by meaning
- Efficient Value Iteration for s-rectangular Robust Markov Decision Processes (ICML 2024 · similarity 0.91)
- Provable Policy Gradient for Robust Average-Reward MDPs Beyond Rectangularity (ICML 2025 · similarity 0.90)
- On the Complexity of Discounted Robust MDPs with $L_p$ Uncertainty Sets (NeurIPS 2026 · similarity 0.90)
- Online MDP with Prototypes Information: A Robust Adaptive Approach (AAAI 2025 · similarity 0.89)
- Soft Robust MDPs and Risk-Sensitive MDPs: Equivalence, Policy Gradient, and Sample Complexity (ICLR 2024 · similarity 0.89)
- Accelerated Policy Gradient for s-rectangular Robust MDPs with Large State Spaces (ICML 2024 · similarity 0.89)
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.
