Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 144.77 +/- 80.11
+      value: -126.24 +/- 64.89
       name: mean_reward
       verified: false
 ---
@@ -30,9 +30,9 @@ model-index:
   ```python
   {'exp_name': 'ppo'
 'gym_id': 'LunarLander-v2'
-'learning_rate': 0.00025
+'learning_rate': 0.0003
 'seed': 1
-'total_timesteps': 10000000
+'total_timesteps': 50000
 'torch_deterministic': True
 'cuda': True
 'track': False
@@ -49,7 +49,7 @@ model-index:
 'num_minibatches': 4
 'update_epochs': 4
 'norm_adv': True
-'clip_coef': 0.2
+'clip_coef': 0.1
 'clip_vloss': True
 'ent_coef': 0.01
 'vf_coef': 0.5

logs/events.out.tfevents.1694550892.17a722d28ef8.3254.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f017da30d6b271cc7cae9f16b7b700581217c25d56b25a9223719cb87776c21c
+size 69838

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:024d48e724ccbea8527a008a65a77efe490801449864c8e7f1cbc8e4d102bf10
-size 42597
+oid sha256:d7daef2b47c97523a3d74b1f560816ff9f209db751eee0ba17016d5d2b24a3ad
+size 42469

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 144.77304518663797, "std_reward": 80.1087037178352, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-12T18:27:21.792365"}
+{"env_id": "LunarLander-v2", "mean_reward": -126.24220068973128, "std_reward": 64.88954937922668, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-12T20:35:26.533104"}