Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -128.63 +/- 47.59
+      value: -132.04 +/- 71.07
       name: mean_reward
       verified: false
 ---
@@ -32,7 +32,7 @@ model-index:
 'gym_id': 'LunarLander-v2'
 'learning_rate': 0.0003
 'seed': 1
-'total_timesteps': 50000
+'total_timesteps': 100000
 'torch_deterministic': True
 'cuda': True
 'track': False

logs/events.out.tfevents.1694551899.17a722d28ef8.7439.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:258f1b9880b9039db6a9520376d7b35b9add22e7adf919d58b51d214f4e902fc
+size 228431

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d57d2ae425d2852894c1be7323b1b649e7efb6a73ea9dfa699a82e4c9168692c
+oid sha256:1b6fc3e32b48291e5f435c30faae18c9cc71fb6911b747cbee983325fe77dbf9
 size 42469

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -128.62861398357782, "std_reward": 47.588716969463384, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-12T20:49:05.094148"}
+{"env_id": "LunarLander-v2", "mean_reward": -132.03725269892158, "std_reward": 71.07413500134216, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-12T20:52:55.455294"}