Research map / Reinforcement learning / MDPs and planning
Hindsight Optimization for Hybrid State and Action MDPs
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 |
|---|---|---|---|
| sample multiple futures (HOP) instead of mean determinization (ablation) | HSA-HOP · Reservoirs 50 | average accumulated reward: -2.32 -> -2.27 (x10^5) | Helped |
| sample multiple futures (HOP) instead of mean determinization (ablation) | HSA-HOP · Power Generation | average accumulated reward | Helped |
| sample multiple futures (HOP) instead of mean determinization (ablation) | HSA-HOP · Icetrack | average accumulated reward | Helped |
| couple first action across futures (HOP) instead of consensus majority vote (ablation) | HSA-HOP · Reservoirs 40 | average accumulated reward: -1.78 -> -1.51 (x10^5) | Helped |
| couple first action across futures (HOP) instead of straight line plan (open loop) (ablation) | HSA-HOP · Reservoirs 50 | average accumulated reward: -2.29 -> -2.27 (x10^5) | No clear effect |
| couple first action across futures (HOP) instead of straight line plan (open loop) (ablation) | HSA-HOP · Icetrack | average accumulated reward | Helped |
| HSA-HOP vs no-op policy | HSA-HOP · Reservoirs 50 | average accumulated reward: -4.38 -> -2.27 (x10^5) | Helped |
| HSA-HOP vs mean determinization | HSA-HOP · Reservoirs 30 | average accumulated reward: -2.42 -> -2.4 (x10^5) | No clear effect |
Closest papers by meaning
- Solving Robust Markov Decision Processes: Generic, Reliable, Efficient (AAAI 2025 · similarity 0.86)
- Deterministic Policy Gradient Primal-Dual Methods for Continuous-Space Constrained MDPs (AAAI 2025 · similarity 0.86)
- Sequential Monte Carlo for Policy Optimization in Continuous POMDPs (NeurIPS 2025 · similarity 0.85)
- A Surprisingly Simple Continuous-Action POMDP Solver: Lazy Cross-Entropy Search Over Policy Trees (AAAI 2024 · similarity 0.85)
- Soft Robust MDPs and Risk-Sensitive MDPs: Equivalence, Policy Gradient, and Sample Complexity (ICLR 2024 · similarity 0.85)
- Beyond Stationarity: Convergence Analysis of Stochastic Softmax Policy Gradient Methods (ICLR 2024 · 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.