Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -140.21 +/- 96.70
+      value: -69.74 +/- 103.96
       name: mean_reward
       verified: false
 ---
@@ -38,12 +38,12 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 50000
-'learning_rate': 0.001
+'learning_rate': 0.00102
 'num_envs': 5
 'num_steps': 128
 'anneal_lr': True
 'gae': True
-'gamma': 0.98
+'gamma': 0.93
 'gae_lambda': 0.99
 'num_minibatches': 4
 'update_epochs': 5

logs/events.out.tfevents.1701201946.e705ad2e6486.21662.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d1e5863ce799097f5a05eb7b503008deb2e5caee39ea9674fa285b5e30a9931
+size 70536

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f102ef6e63a4063d97ab5f1e7b9d91ff0523249fdcb6462fc28aefd1f44a5795
+oid sha256:2c4b7a3e7cb8d6883d4fe91195511c3ce9edc21d60275869a9f4ff2b0fabc98f
 size 42898

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -140.20728842432968, "std_reward": 96.69559821341724, "n_evaluation_episodes": 10, "eval_datetime": "2023-11-28T20:04:19.003061"}
+{"env_id": "LunarLander-v2", "mean_reward": -69.74356884696803, "std_reward": 103.95500882157647, "n_evaluation_episodes": 10, "eval_datetime": "2023-11-28T20:07:00.471334"}