AI Training Analytics & Rich DB Portal
Analyze RL rewards, loss functions, actions, and PostgreSQL records in real-time
Total Timesteps
0
Latest Step: #0
Latest Reward
0.0000
Avg: 0.0000
Avg Policy Loss
0.0000
PPO Gradient Loss
Avg Value Loss
0.0000
Critic Function Loss
Exploration Entropy
0.0000
Policy Entropy RateReward Curve (Step vs Reward)
Live Execution Console (main.py output)
Idle
System initialized. Ready to execute trading agent.
Table: ai_learning_progress
| Step # | Reward | Traded Action | Policy Loss | Value Loss | Entropy | Timestamp | Actions |
|---|---|---|---|---|---|---|---|
| Loading rich database records... | |||||||
Showing 0 - 0 of 0 records
Page 1 of 1
Infrastructure & Traefik Routing Configuration
Active Domain
couldautomate.cloud
Reverse Proxy
Traefik v2.11 (SSL/TLS Enabled)
Database Backend
PostgreSQL 15 (Alpine Container)
Web Framework
FastAPI + Uvicorn Async Server
Traefik Router Rules Enabled:
Host(`couldautomate.cloud`) || Host(`cloudautomate.cloud`) || Host(`www.couldautomate.cloud`) || Host(`www.cloudautomate.cloud`)