Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 49.40 +/- 47.81
+      value: 134.70 +/- 108.61
       name: mean_reward
       verified: false
 ---
@@ -27,5 +27,14 @@ model-index:
   This is a trained model of a REINFORCE agent playing Pixelcopter-PLE-v0.
 
   # Hyperparameters
-  [('hp_seed', 1), ('hp_torch_deterministic', True), ('hp_nb_frames', 8), ('hp_total_timesteps', 1005000), ('hp_learning_t', 500), ('hp_num_envs', 12), ('hp_learning_rate', 0.0001), ('hp_gamma', 0.99), ('hp_buffer_size', 10000), ('hp_batch_size', 32)]
+  hp_seed: 1
+hp_torch_deterministic: True
+hp_nb_frames: 8
+hp_total_timesteps: 1005000
+hp_learning_t: 500
+hp_num_envs: 12
+hp_learning_rate: 0.0001
+hp_gamma: 0.99
+hp_buffer_size: 10000
+hp_batch_size: 32
   

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 49.4, "std_reward": 47.81464210887707, "n_evaluation_episodes": 10, "eval_datetime": "2024-04-01T08:54:12.988925"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 134.7, "std_reward": 108.60851716140867, "n_evaluation_episodes": 10, "eval_datetime": "2024-04-01T08:57:55.395128"}