Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -191.80 +/- 122.14
+      value: 102.34 +/- 101.03
       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': 1000000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1684597422.4c1e86e3ea1e.12028.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9dd5b189efc7d6d76289c397c568cc2cf9804eb790fd6bf2f0e4fc3e2b73b1fa
+size 1006249

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdcf78178ab033a93b34f7326d70cc42208f7483f1f35803a03aad5050e0f842
+oid sha256:4abef1596f159d487d84d675dac8f49da48d0ac270d805d5c39bfc2c3e9f9286
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -191.795194208305, "std_reward": 122.14424719489729, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-20T15:39:58.242189"}
+{"env_id": "LunarLander-v2", "mean_reward": 102.33842796367387, "std_reward": 101.02542582553068, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-20T16:13:48.670542"}