Reinforcement Learning on ishift
0.03TimeMungojerrie
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| Mungojerriestates=4, prod.=29, c=-1, ε=0.1, α=0.1, η=0.1, train-steps=10k2025.05 | 0.03 | — | — | |
| Q-learning with reduction (Bozkurt et al. 2020)states=4, prod.=29, c=-1, ε=0.1, α=0.1, η=0.1, train-steps=10k2025.05 | — | — | 0.02 | |
| Q-learning with reduction (Hahn et al. 2019)states=4, prod.=29, c=-1, ε=0.1, α=0.1, η=0.1, train-steps=10k2025.05 | — | 0.01 | — |