Research map / Reinforcement learning / MDPs and planning
Belief-Dependent Macro-Action Discovery in POMDPs using the Value of Information
Genevieve Flaspohler, Nicholas A. Roy, John W. Fisher III
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 VoI-based macro-actions instead of closed-loop planning | POMDP planner · Boundary Dynamics, alpha=0.20 | total reward: 2800.2 -> 3039.5 | Improved |
| use VoI-based macro-actions instead of closed-loop planning | POMDP planner · Random Walk Dynamics | total reward: 3035.8 -> 3050.8 | No clear effect |
| use VoI macro-actions instead of fixed-length macro-actions (T=15) | POMDP planner · Boundary Dynamics, alpha=0.20 | total reward: 2584.3 -> 3039.5 | Improved |
| use VoI macro-actions instead of fixed-length macro-actions (T=15) | POMDP planner · Random Walk Dynamics | total reward: 2946.6 -> 3050.8 | Improved |
| use VoI macro-actions instead of closed-loop planning | POMDP planner · Boundary Dynamics, alpha=0.20 | empirical delta_B: 0.45 -> 0.29 | Improved |
| use VoI macro-actions instead of closed-loop planning | POMDP planner · Random Walk Dynamics | empirical delta_B: 0.42 -> 0.31 | Improved |
| use fixed-length macro-actions instead of VoI macro-actions | POMDP planner · Boundary Dynamics, alpha=0.20 | empirical delta_B: 0.29 -> 0.17 | Improved |
| use VoI macro-actions instead of closed-loop planning | POMDP planner · Experiment 2 (zone of interest) | average reward: 15.08 -> 18.69 | Improved |
| use VoI macro-actions instead of fixed-length macro-actions | POMDP planner · Experiment 2 (zone of interest) | average reward: 13.03 -> 18.69 | Improved |
| increase VoI threshold tau (ablation) | VoI macro-action policy · Boundary tracking | empirical delta_B | Improved |
| increase VoI threshold tau (ablation) | VoI macro-action policy · Boundary tracking | open-loop fraction of horizon | Improved |
| increase VoI threshold tau (ablation) | VoI macro-action policy · Boundary tracking | realized reward | Mixed |
Closest papers by meaning
- Sequential Monte Carlo for Policy Optimization in Continuous POMDPs (NeurIPS 2025 · similarity 0.88)
- A Surprisingly Simple Continuous-Action POMDP Solver: Lazy Cross-Entropy Search Over Policy Trees (AAAI 2024 · similarity 0.87)
- Learning to Explore in POMDPs with Informational Rewards (ICML 2024 · similarity 0.86)
- Simplifying Complex Observation Models in Continuous POMDP Planning with Probabilistic Guarantees and Practice (AAAI 2024 · similarity 0.86)
- Provable Representation with Efficient Planning for Partially Observable Reinforcement Learning (ICML 2024 · similarity 0.86)
- Learning Logic Specifications for Policy Guidance in POMDPs: an Inductive Logic Programming Approach (AAAI 2025 · similarity 0.86)
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.
