Upload README.md with huggingface_hub

README.md

@@ -17,15 +17,15 @@ PPO-trained agent for [OpenFront.io](https://openfront.io), a multiplayer territ
 - **Architecture:** Actor-Critic with shared backbone (256→256→128)
 - **Map:** world
 - **Opponents:** 5 bots
-- **Episodes trained:** 20
-- **Global steps:** 57109
-- **Best mean reward:** 151.78631000000004
+- **Episodes trained:** N/A
+- **Global steps:** 1638400
+- **Best mean reward:** 31.003479852676392
 
 ## Final Training Metrics
 
-- **Mean reward:** 151.78631000000004
-- **Mean episode length:** 2855.45
-- **Loss:** 4.396657466888428
+- **Mean reward:** 29.898164215087892
+- **Mean episode length:** 3657.29
+- **Loss:** 0.8671517372131348
 
 ## Usage
 
@@ -33,7 +33,7 @@ PPO-trained agent for [OpenFront.io](https://openfront.io), a multiplayer territ
 from train import ActorCritic
 import torch
 
-model = ActorCritic(obs_dim=32, max_neighbors=8)
+model = ActorCritic(obs_dim=78, max_neighbors=16)
 model.load_state_dict(torch.load("best_model.pt", weights_only=True))
 model.eval()
 ```