Research map / Reinforcement learning / MDPs and planning
A Maximum-Entropy Approach to Off-Policy Evaluation in Average-Reward MDPs
Nevena Lazic, Dong Yin, Mehrdad Farajtabar, Nir Levine, Dilan Gorur, Chris Harris, Dale Schuurmans
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 |
|---|---|---|---|
| Estimate the dynamics and use the corresponding optimal controller | Certainty-equivalent approach · Simple LQ system, σ=0.05 | average cost and stability | Hurt |
| Estimate the dynamics and use the corresponding optimal controller | Certainty-equivalent approach · Simple LQ system, otherwise | average cost | Improved |
| Take a single policy-improvement step using a least-squares Monte Carlo estimate of Gβ | Behavior policy · Simple LQ system | average cost | No clear effect |
| Optimize the imputed loss | Imputed-loss method · Simple LQ system, σ≤0.15 | average cost and stability | Hurt |
| Optimize the imputed loss | Imputed-loss method · Simple LQ system, higher σ | average cost | Hurt |
Closest papers by meaning
- Semiparametrically Efficient Off-Policy Evaluation in Linear Markov Decision Processes (ICML 2023 · similarity 0.89)
- Efficient and Sharp Off-Policy Evaluation in Robust Markov Decision Processes (NeurIPS 2024 · similarity 0.88)
- Statistical Tractability of Off-policy Evaluation of History-dependent Policies in POMDPs (ICLR 2025 · similarity 0.87)
- RL in Latent MDPs is Tractable: Online Guarantees via Off-Policy Evaluation (NeurIPS 2024 · similarity 0.87)
- SEMDICE: Off-policy State Entropy Maximization via Stationary Distribution Correction Estimation (ICLR 2025 · similarity 0.87)
- Q-MMR: Off-Policy Evaluation via Recursive Reweighting and Moment Matching (NeurIPS 2026 · similarity 0.87)
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.
