gamma: 0.99
strength: 1.0
keep_checkpoints: 5
max_steps: 100000000
max_steps: 5000000
time_horizon: 256
summary_freq: 10000
threaded: true
behavior: Sorter
signal_smoothing: true
min_lesson_length: 100
threshold: 0.05
threshold: 0.5
value: 2.0
- name: Lesson1
completion_criteria:
threshold: 0.1
threshold: 0.6
value: 4.0
- name: Lesson2
threshold: 0.15
threshold: 0.65
value: 6.0
- name: Lesson3
threshold: 0.2
threshold: 0.7
value: 8.0
- name: Lesson4
threshold: 0.25
threshold: 0.75
value: 10.0
- name: Lesson5
threshold: 0.3
threshold: 0.8
value: 12.0
- name: Lesson6
threshold: 0.35
threshold: 0.85
value: 14.0
- name: Lesson7
threshold: 0.4
threshold: 0.9
value: 16.0
- name: Lesson8
threshold: 0.45
threshold: 0.95
value: 18.0
- name: Lesson9
value: 20.0