Python · Apache-2.0
Jaasssoooonnnnn/FirstLight_CR
Offline Clash Royale AI agent research: native simulation, imitation learning, PPO, and interactive evaluation. 离线对局模拟、模仿学习、强化学习与交互评测。
★ 177
Stars
52 forks · 2 open issues
—
Growth · stale
We stopped seeing this repository in its topic's top results, so its star count is frozen at the date it was last read. Subtracting from a frozen number would read as zero growth, which would be false, so no rate is shown.
18.8
Momentum / 100
see the breakdown below
2mo ago
Created
last push 35d ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 0.0 | — — no measurable rate |
| Acceleration | 15 | 0.0 | needs 7-day and 30-day rates side by side |
| Freshness | 15 | 12.3 | last push 35d ago; decays to zero at 180 days |
| Scale | 15 | 6.5 | 177 stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 18.8 | capped at 35 because growth is unmeasured |
Detail
| Topics | artificial-intelligenceclash-royaledeep-learningdeep-reinforcement-learningdistributed-traininggame-aiimitation-learningmulti-agentppopytorchreinforcement-learningself-play |
| Matched on | AI Agents (multi-agent) |
| Short window | no snapshot 5–10 days old yet |
| Long window | +26 stars over 26 days = 1.0/day |
| Lifetime average | 2.93 stars/day over 60 days |
| First seen here | 2026-10-11 |
| Last read | 19d ago |