AI Training Lab
Real-time reinforcement learning experiments. PPO vs DQN vs A2C training on CogniCore environments with live metric streaming.
📈 Training Curves — Live
Episode reward over time, per algorithm
📊 Live Feed
Real-time training events
🏆 Algorithm Comparison
Final evaluation scores (20 episodes each)
📋 Results Table
Detailed metrics per algorithm
| Rank | Algorithm | Mean Reward | Std | Train Time |
|---|
📊 Cross-Environment Benchmark
PPO performance across all CogniCore environments