Research map / Reinforcement learning / Visual and representation RL
Information-guided Planning: An Online Approach for Partially Observable Problems
Matheus Aparecido Do Carmo Alves, Amokh Varma, Yehia Elkhatib, Leandro Soriano Marcolino
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 |
|---|---|---|---|
| Replace POMCP action selection with information-guided I-UCB (IB-POMCP) | POMCP · MazeHoles (M1) | average reward: 1.56 × 10−2 -> 3.80 × 10−2 | Improved |
| Use IB-POMCP instead of POMCP | POMCP · MazeGridX (M3) | average reward: 2.80 × 10−2 -> 0.96 × 10−2 | Hurt |
| Use IB-POMCP instead of POMCP | POMCP · Foraging U-obstacles (F2) | average reward: 1.17 × 10−2 -> 5.50 × 10−2 | Improved |
| Use IB-POMCP instead of POMCP | POMCP · Foraging Warehouse (F3) | average reward: 5.20 × 10−2 -> 10.73 × 10−2 | Improved |
| Use IB-POMCP instead of POMCP | POMCP · Tiger (T0) | average reward: −4.25 × 102 -> −0.52 × 102 | Improved |
| Use IB-POMCP instead of TB ρ-POMCP | TB ρ-POMCP · Tiger (T0) | average reward: −0.16 × 102 -> −0.52 × 102 | Hurt |
| Use IB-POMCP instead of POMCP | POMCP · LaserTag (LT1) | average reward: −0.90 × 10−1 -> −0.92 × 10−1 | No clear effect |
| Use IB-POMCP instead of POMCP | POMCP · Tag (LT0) | average reward: −0.47 × 10−1 -> −0.36 × 10−1 | Improved |
| Use IB-POMCP instead of POMCP | POMCP · RockSample22 (R0) | average reward: 0.06 × 10−1 -> 0.07 × 10−1 | No clear effect |
| Use IB-POMCP instead of POMCP | POMCP · RockSample44 (R2) | average reward: 0.07 × 10−1 -> 0.09 × 10−1 | Improved |
| Use IB-POMCP instead of POMCP | POMCP · Maze scenarios | planning time | Improved |
| Use IB-POMCP instead of POMCP | POMCP · RockSample scenarios | planning time | Hurt |
Closest papers by meaning
- Learning Logic Specifications for Policy Guidance in POMDPs: an Inductive Logic Programming Approach (AAAI 2025 · similarity 0.87)
- A Bayesian Approach to Online Planning (ICML 2024 · similarity 0.87)
- Partially Observable Hierarchical Reinforcement Learning with AI Planning (Student Abstract) (AAAI 2024 · similarity 0.87)
- Factored Online Planning in Many-Agent POMDPs (AAAI 2024 · similarity 0.87)
- Belief-State Query Policies for User-Aligned POMDPs (NeurIPS 2024 · similarity 0.87)
- Risk-Averse Online POMDP Planning via CVaR of the Immediate Cost with Performance Guarantees (NeurIPS 2026 · 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.
