Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -183.85 +/- 141.81
+      value: -185.62 +/- 118.74
       name: mean_reward
       verified: false
 ---
@@ -45,7 +45,7 @@ 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.1676822534.c53965806e42.1.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17f872740cd1f556e0eb117f57f1909401c59f5d0fa29a4cf543ecfe6a451fd8
+size 227169

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4c83dd6abea527a09cdda8b86abba56df6404587c35aefd771b09b35efc3dac
+oid sha256:3b89c2cb977643285b19a916a861bf74f0cf246f5c6281bf6754b40873e5da54
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -183.84844791551527, "std_reward": 141.80741035088553, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-19T16:00:55.985696"}
+{"env_id": "LunarLander-v2", "mean_reward": -185.62439945649697, "std_reward": 118.74480264761978, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-19T16:02:54.362380"}