Research map / Bandits and online learning / RL theory and MDPs
Fast-Tracking Stationary MOMDPs for Adaptive Management Problems
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 |
|---|---|---|---|
| initialize MO-SARSOP with MDP-corner lower bound instead of its default lower bound | MO-SARSOP · Aedes 7 islands | initial value: 11.7 -> 16.7 | Helped |
| initialize MO-SARSOP with MDP-corner lower bound | MO-SARSOP · Aedes 8 islands | initial value: 12.2 -> 17.4 | Helped |
| initialize MO-SARSOP with MDP-corner lower bound | MO-SARSOP · Grey-tailed tattler | initial value: 4987 -> 5167 | Helped |
| initialize MO-SARSOP with MDP-corner lower bound | MO-SARSOP · Red knot pearsonii | initial value: 6049 -> 6049 | No clear effect |
| initialize MO-SARSOP with MDP-corner lower bound | MO-SARSOP · Red knot pearsonii | optimality gap reduction speed | Helped |
| initialize MO-SARSOP with MDP-corner lower bound | MO-SARSOP · Red knot rogersi | initial value: 6906 -> 6947 | Helped |
| initialize MO-SARSOP with MDP-corner lower bound | MO-SARSOP · Aedes 7 islands | initialization time: 159 s -> 165 s | No clear effect |
| initialize Perseus with MDP-corner lower bound instead of constant minimum-reward value | Perseus · Grey-tailed tattler | initial value: 836 -> 5167 | Helped |
| initialize Perseus with MDP-corner lower bound | Perseus · Aedes 7 islands | initialization time: 0 s -> 76 s | Hurt |
| initialize Perseus with MDP-corner lower bound | Perseus · Tattler value over time | value over time | Helped |
Closest papers by meaning
- Sequential Monte Carlo for Policy Optimization in Continuous POMDPs (NeurIPS 2025 · similarity 0.82)
- Decision-Making for Land Conservation: A Derivative-Free Optimization Framework with Nonlinear Inputs (AAAI 2024 · similarity 0.82)
- A Single-Loop Robust Policy Gradient Method for Robust Markov Decision Processes (ICML 2024 · similarity 0.82)
- When to Sense and Control? A Time-adaptive Approach for Continuous-Time RL (NeurIPS 2024 · similarity 0.81)
- Efficient and Sharp Off-Policy Evaluation in Robust Markov Decision Processes (NeurIPS 2024 · similarity 0.81)
- Near-Optimal Policy Identification in Robust Constrained Markov Decision Processes via Epigraph Form (ICLR 2025 · similarity 0.81)
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.