Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -115.06 +/- 29.28
+      value: -142.35 +/- 52.39
       name: mean_reward
       verified: false
 ---
@@ -29,7 +29,7 @@ model-index:
   # Hyperparameters
   ```python
   {'exp_name': 'ppo'
-'seed': 1
+'seed': 653623
 'torch_deterministic': True
 'cuda': True
 'track': False
@@ -39,7 +39,7 @@ model-index:
 'env_id': 'LunarLander-v2'
 'total_timesteps': 250000
 'learning_rate': 1e-05
-'num_envs': 4
+'num_envs': 16
 'num_steps': 128
 'anneal_lr': True
 'gae': True
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'irow/ppo-LunarLander-v2'
-'batch_size': 512
-'minibatch_size': 128}
+'batch_size': 2048
+'minibatch_size': 512}
   ```
   

logs/events.out.tfevents.1684423602.irow-pc.66820.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1957e01e2ba3778a85bb639b2edc6a69bc3645ec780812f32e26551d61066a34
+size 366750

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0880b3fff8754fdc27aa13e5ce7578237f78b0a02a618452c2b0b35f816ce812
+oid sha256:c6e8269fcf8e64e1962fd0606e566b38e3cb6d84e1595d86d31173fe45b93bd7
 size 42817

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -115.05908674477487, "std_reward": 29.280940153403936, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-18T09:18:51.159521"}
+{"env_id": "LunarLander-v2", "mean_reward": -142.34720310087874, "std_reward": 52.38909631768608, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-18T09:27:40.667503"}