README.md

metadata

title: K1RL QUASAR — Volatility 75 (1s)
emoji: 💛
colorFrom: yellow
colorTo: yellow
sdk: docker
pinned: false
license: mit
short_description: 8 quantum AI agents trading V75 (1s) on Deriv 24/7

⚡ K1RL QUASAR — VOLATILITY 75 (1s)

💛 THE YELLOW RANGER — Perfect Transfer · Zero Domain Shift

---

🧠 What is K1RL QUASAR?

K1RL QUASAR is an 8-agent quantum-enhanced reinforcement learning trading system that autonomously trades synthetic indices on the Deriv platform — 24 hours a day, 7 days a week, with zero human intervention.

Each agent runs an Actor-Critic network enhanced with Qiskit quantum circuits, coordinating via QMIX value decomposition and a QuantumVotingSystem where all 6 trading agents vote on every action before execution.

---

💛 Yellow Ranger Profile — V75 (1s)

The Yellow Ranger is the most faithful transfer in the entire fleet. Identical 75% volatility to the V75 foundation model — the agents already know this market. Only the tick cadence changes from variable ~2s to a fixed 1 second.

Property	Value
🎯 Index	Volatility 75 Index (1s)
📡 Deriv Symbol	1HZ75V
⚡ Volatility	75% — identical to V75 pretrain
🕐 Tick Speed	Every 1 second (vs ~2s variable on R_75)
🧬 Pretrained From	V75 foundation model (voyage v1)
📦 Voyage	v5 → saves to V100/v5/
🔑 Redis Password	k1rl_v751s_8e4b2f6a0d3c9517
🏃 Transfer Ratio	1.0000 — perfect match

---

⭐ Why V75 (1s) is Special

The pretrained V75 model (R_75, voyage v1) learned the 75% volatility distribution from thousands of training iterations. 1HZ75V runs the exact same underlying distribution — just with a fixed 1-second tick interval.

• ✅ Feature magnitudes nearly identical
• ✅ Reward scaling requires no adjustment
• ✅ No directional bias correction needed
• ✅ Fastest expected convergence of any index in the fleet
• ✅ Essentially zero domain shift

---

🏗️ Architecture

┌─────────────────────────────────────────────────────┐
│              K1RL QUASAR — V75 (1s)                 │
├──────────────┬──────────────┬───────────────────────┤
│  Features.py │  Rewards.py  │   quasar_main4.py     │
│  1HZ75V      │  V75_1S      │   8 Actor-Critic      │
│  Tick Data   │  Reward Sig  │   QMIX + Voting       │
├──────────────┴──────────────┴───────────────────────┤
│               Redis (V75_1S: namespace)              │
├─────────────────────────────────────────────────────┤
│         HuggingFace Spaces — CPU Basic               │
└─────────────────────────────────────────────────────┘

---

🗺️ Fleet Voyage Map

Voyage	Space	Symbol	Pretrain	Theme
v1	K1RL-Quasar-Volatility-75	R_75	🏛️ Foundation	⬛ Black
v2	K1RL-Quasar-Crash-500	CRASH500	v1	🔵 Blue
v3	K1RL-Quasar-Volatility-50-1s	1HZ50V	v1	💚 Green
v4	K1RL-Quasar-Volatility-100-1s	1HZ100V	v1	🔴 Red
v5	K1RL-Quasar-Volatility-75-1s	1HZ75V	v1	💛 Yellow
v6	K1RL-Quasar-Crash-1000	CRASH1000	v2	🌸 Pink

---

📊 Checkpoints

• Dataset: KarlQuant/k1rl-checkpoints
• Path: V100/v5/
• Strategy: Resume from v5 → fallback warm-start from v1 (V75)

---

Built with PyTorch · Qiskit · Redis · HuggingFace Spaces

K1RL QUASAR Fleet — Autonomous Quantum Trading