Push agent to the Hub

README.md

@@ -17,18 +17,18 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -209.87 +/- 158.81
+      value: -178.50 +/- 139.87
       name: mean_reward
       verified: false
 ---
 
-  # PPO Agent Playing LunarLander-v2
-
-  This is a trained model of a PPO agent playing LunarLander-v2.
+      # PPO Agent Playing LunarLander-v2
     
-  # Hyperparameters
-  ```python
-  {'exp_name': 'ppo'
+      This is a trained model of a PPO agent playing LunarLander-v2.
+        
+      # Hyperparameters
+      ```python
+      {'exp_name': 'ppo'
 'seed': 1
 'torch_deterministic': True
 'cuda': True
@@ -37,8 +37,8 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 50000
-'learning_rate': 5e-05
+'total_timesteps': 20000
+'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True
@@ -57,5 +57,5 @@ model-index:
 'repo_id': 'MRNH/LunarLander-v2'
 'batch_size': 512
 'minibatch_size': 128}
-  ```
-  
+      ```
+      

logs/events.out.tfevents.1691957629.bcadd1928d08.3541.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43906a167059d4b93ff812c84cd8fb97d20033df994f44c8ff010fce97754a56
+size 45975

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45c60c95580bc4b48947f37d9d0e2ac7c46e4bd32ce9e2eb618bc2523bafc229
+oid sha256:a2d25459cd74ef1f96e7a4bd40dda3f64e2ce94873ed1c35e687117801609e89
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -209.8674404134129, "std_reward": 158.80703972840834, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-12T15:21:54.147140"}
+{"env_id": "LunarLander-v2", "mean_reward": -178.49865011255935, "std_reward": 139.87497653293718, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-13T20:14:10.767068"}