Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
Bayesian Risk Markov Decision Processes
Yifan Lin, Yuxuan Ren, Enlu Zhou
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 nested Bayesian CVaR risk with α=0.4 instead of nominal MLE planning | MDP offline planning · Gambler's betting, θᶜ=0.45, N=10 | mean actual cost: -6.30 -> -8.82 | Improved |
| Use nested Bayesian CVaR risk with α=0.4 instead of nominal MLE planning | MDP offline planning · Gambler's betting, θᶜ=0.45, N=10 | variance actual cost: 26.46 -> 9.92 | Improved |
| Approximate rather than exact dynamic programming (ablation) | BR-MDP, Gambler's betting · Gambler's betting, θᶜ=0.45, N=10 | time(s): 65.52 -> 5.02 | Improved |
| Approximate rather than exact dynamic programming (ablation) | BR-MDP · Gambler's betting, θᶜ=0.45, N=10 | mean actual cost: -8.82 -> -8.26 | No clear effect |
| Use a worst-case DR-MDP policy rather than Bayesian risk planning | MDP offline planning · Inventory control, θᶜ=12, N=10 | mean actual cost: 81.63 -> 99.77 | Hurt |
| Increase the CVaR confidence level to α=1 (ablation) | BR-MDP, Gambler's betting · Gambler's betting, θᶜ=0.45, N=10 | mean actual cost: -8.82 -> -2.38 | Hurt |
| Increase the CVaR confidence level (ablation) | BR-MDP, Gambler's betting · Gambler's betting, θᶜ=0.45 | actual performance conservativeness | Hurt |
| Increase data size from N=5 to N=100 (ablation) | BR-MDP versus Nominal · Gambler's betting, θᶜ=0.45 | mean actual cost: -7.83 -> -9.26; -5.88 -> -9.45 | Mixed |
Closest papers by meaning
- Approximate Bilevel Difference Convex Programming for Bayesian Risk Markov Decision Processes (AAAI 2025 · similarity 0.90)
- Soft Robust MDPs and Risk-Sensitive MDPs: Equivalence, Policy Gradient, and Sample Complexity (ICLR 2024 · similarity 0.87)
- Solving Robust Markov Decision Processes: Generic, Reliable, Efficient (AAAI 2025 · similarity 0.87)
- Risk Estimation in a Markov Cost Process: Lower and Upper Bounds (ICML 2024 · similarity 0.85)
- Planning and Learning in Average Risk-aware MDPs (NeurIPS 2025 · similarity 0.85)
- Decision Making under the Exponential Family: Distributionally Robust Optimisation with Bayesian Ambiguity Sets (ICML 2025 · 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.
