Adaptive Planning on Deterministic dynamics and discounted rewards planning problems
2Simple Regret Upper BoundPlaTγPOOS
Evaluation results
| Method | Links | |
|---|---|---|
| PlaTγPOOSγ²κ regime=γ²κ ≤ 1, Noise condition (i)=High noise (i), Noise condition (ii) or (iii)=High noise (ii), Branching factor κ=N/A2026.04 | 2 | |
| PlaTγPOOSγ²κ regime=γ²κ ≤ 1, Noise condition (i)=Low noise (i), Noise condition (ii) or (iii)=High noise (ii), Branching factor κ=N/A2026.04 | 2 | |
| PlaTγPOOSγ²κ regime=γ²κ ≤ 1, Noise condition (i)=Low noise (i), Noise condition (ii) or (iii)=Low noise (ii), Branching factor κ=κ > 12026.04 | 2 | |
| PlaTγPOOSγ²κ regime=γ²κ ≥ 1, Noise condition (i)=High noise (i), Noise condition (ii) or (iii)=High noise (iii), Branching factor κ=N/A2026.04 | 2 | |
| PlaTγPOOSγ²κ regime=γ²κ ≥ 1, Noise condition (i)=High noise (i), Noise condition (ii) or (iii)=Low noise (iii), Branching factor κ=N/A2026.04 | 2 | |
| PlaTγPOOSγ²κ regime=γ²κ ≥ 1, Noise condition (i)=Low noise (i), Noise condition (ii) or (iii)=High noise (iii), Branching factor κ=N/A2026.04 | 2 | |
| PlaTγPOOSγ²κ regime=γ²κ ≥ 1, Noise condition (i)=Low noise (i), Noise condition (ii) or (iii)=Low noise (iii), Branching factor κ=N/A2026.04 | 2 |