facebookresearch / rebel
An algorithm that generalizes the paradigm of self-play reinforcement learning and search to imperfect-information games.
Summary
   |
|||
| Main Code: 4,647 LOC (36 files) = CC (46%) + PY (28%) + H (23%) + YAML (1%) Secondary code: Test: 493 LOC (4); Generated: 0 LOC (0); Build & Deploy: 6 LOC (1); Other: 123 LOC (3); |
|||
| Duplication: 2% | |||
| File Size: 0% long (>1000 LOC), 39% short (<= 200 LOC) | |||
| Unit Size: 19% long (>100 LOC), 45% short (<= 10 LOC) | |||
| Conditional Complexity: 15% complex (McCabe index > 50), 54% simple (McCabe index <= 5) | |||
|
|
Logical Component Decomposition: primary (9 components) | ||
|
|
1 year, 6 months old
|
||
|
|
0% of code updated more than 50 times Also see temporal dependencies for files frequently changed in same commits. |
||
| Goals: Keep the system simple and easy to change (4) | |||
Latest commit date: 2021-01-10
|
0
commits
(30 days)
0
contributors
(30 days) |
|