Reinforcement Learning on grid5x5
0.62TimeMungojerrie
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| Mungojerriestates=25, prod.=100, c=-1, ε=0.1, α=0.5, η=0.1, train-steps=200k2025.05 | 0.62 | — | — | |
| Q-learning with reduction (Bozkurt et al. 2020)states=25, prod.=100, c=-1, ε=0.1, α=0.5, η=0.1, train-steps=200k2025.05 | — | — | 1.02 | |
| Q-learning with reduction (Hahn et al. 2019)states=25, prod.=100, c=-1, ε=0.1, α=0.5, η=0.1, train-steps=200k2025.05 | — | 1.12 | — |