Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -258.23 +/- 180.57
+      value: -132.75 +/- 45.39
       name: mean_reward
       verified: false
 ---
@@ -37,8 +37,8 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 50000
-'learning_rate': 0.0002
+'total_timesteps': 100000
+'learning_rate': 0.0001
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True

logs/events.out.tfevents.1708628851.27eacc152b6c.14249.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c85e834a06122b13a7c3c965ca7a30fa6155cc2df6e712ba09d2e9d7ef85891c
+size 220572

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a7c910ed466c110d3c1dd9d029e229edfa1ed35b3f8a9d8000829f3c830c85e
+oid sha256:0bab92906bdc8a65a6943246324cca4dad34aaf61f5a775a347463b5555f99f0
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -258.22764967462064, "std_reward": 180.5733028573796, "n_evaluation_episodes": 10, "eval_datetime": "2024-02-22T18:55:14.222219"}
+{"env_id": "LunarLander-v2", "mean_reward": -132.75412597112125, "std_reward": 45.39155430237143, "n_evaluation_episodes": 10, "eval_datetime": "2024-02-22T19:08:55.136470"}