🕹️Fullscreen
♻️Load
⏸️Pause
🚀Accel
⬜None
⬅️Left
➡️Right
🧭Guide
🎮Games
ℹ️About
Agent 1:
📊Dashboard
🔬Analysis
RR Platform v1.0.0
Algorithm Selection
Learning Method:
Q-Table
DQN
Strategy:
ε-greedy
Softmax
Hyperparameters
Learning Rate (α):
0.5
Discount Factor (γ):
0.95
Exploration Rate (ε):
0.2
Temperature (τ):
5.0
Optimism (ψ):
1
Delay (ms):
50
Q-Table Stats
💾 Export
📂 Import
🧹 Clear
State Bins
[10×10]
Actions
[5]
Total Data
102 / 500
Coverage
20.4%
Sync
Syncing...
Chart Controls
Source:
Q-Table
DQN
Projection:
X-axis:
Y-axis:
Slice Pos:
Live
Manual
Sliders