Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -153.26 +/- 83.99
+      value: -183.18 +/- 71.91
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 50000
+'total_timesteps': 100000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1678485728.22735be74021.3683.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9a2c3136491f85b96a4127b9815a333001c18cbd53ee72c98d5e9a51b593849
+size 216805

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3262cb9f8d71762568958150de91d2adbb7385c87e56d48030e8005230aa5d95
+oid sha256:bcd2d09ce108a051e2e384d5e01bda71dd42ff9b117e243d3d4f61911fd43a9d
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -153.2602891224624, "std_reward": 83.99366835392043, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-10T22:01:31.846494"}
+{"env_id": "LunarLander-v2", "mean_reward": -183.1849882483027, "std_reward": 71.90837939316914, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-10T22:03:27.822473"}