Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -178.10 +/- 100.49
+      value: -199.43 +/- 118.10
       name: mean_reward
       verified: false
 ---
@@ -30,7 +30,7 @@ model-index:
   ```python
   {'exp_name': 'ppo'
 'gym_id': 'LunarLander-v2'
-'learning_rate': 0.0003
+'learning_rate': 0.00025
 'seed': 1
 'total_timesteps': 100000
 'torch_deterministic': True

logs/events.out.tfevents.1694552956.17a722d28ef8.11840.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d83e2a4172ad7ca4d09b998ff21538292e791fbe5db32622e44f3a12dc1082d1
+size 140992

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ebf3465c38ec32051261e720f626890cc85ca8688e353209b67003d4a9114ce
+oid sha256:ce0abad7b782e3f9211f6661be300830dbc09760ce9c1906d33ba5bfd09209e3
 size 42469

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -178.09648291318484, "std_reward": 100.491451215421, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-12T21:06:33.369776"}
+{"env_id": "LunarLander-v2", "mean_reward": -199.42643945785275, "std_reward": 118.09537541111304, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-12T21:10:19.021390"}