{
  "rewards": [
    0,
    1
  ],
  "success_probabilities": [
    0,
    1
  ],
  "terminal_potentials": [
    2,
    0
  ],
  "episodes": 100,
  "seeds": [
    7,
    17
  ],
  "learning_rate": 0.1,
  "discount": 1,
  "evaluation_runs": 100
}