Research map / Reinforcement learning / MDPs and planning
Near Optimality of Finite Memory Feedback Policies in Partially Observed Markov Decision Processes
Ali Kara, Serdar Yuksel
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 |
|---|---|---|---|
| increase window length N | finite window policy · machine repair POMDP (eps=0.3, kappa=0.2, theta=0.1) | value error and robustness error | Improved |
| make the measurement channel more informative (eps 0.3 to 0.01) | finite window policy · machine repair POMDP | error decrease with window size | Improved |
| use Dobrushin coefficient alpha below 1 (eps=0.3, kappa=0.4, theta=0.3) | finite window policy · machine repair POMDP | convergence rate of errors: alpha=0.7 | No clear effect |
| use three-level quantized observations {-q,0,q} instead of two-level {-q,q} | exponential filter stability condition · Gaussian example, sigma_t/t = 1.4 | minimum sigma_q/q: 0.6 -> 0.39 | Improved |
Closest papers by meaning
- Scalable Policy-Based RL Algorithms for POMDPs (NeurIPS 2025 · similarity 0.89)
- Multi-Environment POMDPs with Finite-Horizon Objectives (NeurIPS 2026 · similarity 0.89)
- Sequential Monte Carlo for Policy Optimization in Continuous POMDPs (NeurIPS 2025 · similarity 0.89)
- Provable Representation with Efficient Planning for Partially Observable Reinforcement Learning (ICML 2024 · similarity 0.89)
- Revelations: A Decidable Class of POMDPs with Omega-Regular Objectives (AAAI 2025 · similarity 0.88)
- A Policy Gradient Method for Confounded POMDPs (ICLR 2024 · similarity 0.88)
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.
