Update README.md: add 25M steps checkpoint and adjust training timesteps

README.md

@@ -28,10 +28,10 @@ This is a PPO agent trained using Stable Baselines3 and Gymnasium on a Mario-lik
 
 ## Training Timesteps & Checkpoints
 
-| Checkpoint                                              | Timesteps  | Notes                |
-| ------------------------------------------------------- | ---------- | -------------------- |
-| [20M Steps](checkpoints/simple/20M_steps/mario_ppo.zip) | 20,000,000 | Early-stage learning |
-| [50M Steps](checkpoints/simple/50M_steps/mario_ppo.zip) | 50,000,000 | Better stability     |
+| Checkpoint                                                       | Timesteps  | Notes                |
+| ---------------------------------------------------------------- | ---------- | -------------------- |
+| [25M Steps](checkpoints/simple/25M_steps/mario_ppo_25000000.zip) | 25,000,000 | Early-stage learning |
+| [50M Steps](checkpoints/simple/50M_steps/mario_ppo.zip)          | 50,000,000 | Better stability     |
 
 ## Usage
 

checkpoints/simple/25M_steps/mario_ppo_25000000.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63e083df68672c3ee1a4aa14cffe2de546305e2c61fa0b7c6ad34b20db578786
+size 289910411