Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -151.21 +/- 88.39
+      value: -130.28 +/- 105.01
       name: mean_reward
       verified: false
 ---
@@ -43,7 +43,7 @@ model-index:
 'num_steps': 128
 'anneal_lr': True
 'gae': True
-'gamma': 0.99
+'gamma': 0.95
 'gae_lambda': 0.95
 'num_minibatches': 4
 'update_epochs': 4

logs/events.out.tfevents.1732732031.45d7fe83a2d9.7999.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc8310eb198c79476463df3bd7de662d3dcdb7adde0c9f06f25ddde43e4bec7b
+size 187101

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2608c32e3af11cb6a92dd4cf40cebd87d6a0d08801d4bacb52ae4edb8f3a237
+oid sha256:7083a3e7824a346f3b4fa5167cfa6be231c88424642d103540240370aa63eee3
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -151.21312477880878, "std_reward": 88.39487193931222, "n_evaluation_episodes": 10, "eval_datetime": "2024-11-27T18:24:44.858087"}
+{"env_id": "LunarLander-v2", "mean_reward": -130.2848482139971, "std_reward": 105.01226180127931, "n_evaluation_episodes": 10, "eval_datetime": "2024-11-27T18:28:49.933082"}