Game_Playing_Agent Muzammil592 · COMPLETED
Coded a self-play agent from scratch, mastering the Bellman equation and MDP fundamentals. Hit a real-world RL bug where the agent wouldn't block threats due to missing terminal signals; fixed it using an episode history replay. Seeing win rates hit 97% after fixing the reward assignment is incredibly rewarding.
github.com/Muzammil592/Game_Playing_Agent · ★ 2 · Forks 0 · Size 797 KB
SUMMARY
Technologies 3
Scored 3
Observed 3
Practices 6
Evidence 3
Skips 0
COVERAGE
Analyzed 17 files · 9 commits · 0 API calls
TECHNOLOGIES & DEPTH
Markdown LANGUAGE Depth 70
2 files · PRODUCTION
Python LANGUAGE Depth 70
8 files · PRODUCTION
NumPy LIBRARY Depth 81
7 files · PRODUCTION
PRACTICES
documentation · observedautomated_tests · absentcontinuous_integration · absentcontainerization · absentlinting · absentformatting · absent
ACTIVITY & OWNERSHIP
First commit 2026-06-27
Last commit 2026-06-29
Active months 1
Commits 9