Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -36.39 +/- 28.79
+      value: 70.49 +/- 43.95
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 500000
+'total_timesteps': 1000000
 'learning_rate': 0.0003
 'num_envs': 16
 'num_steps': 1024

logs/events.out.tfevents.1684363339.a82ae466d056.3550.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78cdaf865eab8ea7a3889a534ccce8fc495b245d3afcd7c3788d92086512d15a
+size 490762

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:292c0e5ee58a7540329d1c1ef08ce0abe25ac104562ce55a153840de1dd836cf
+oid sha256:e17523fbeebb0d4fdb79282b61a2d03d0c70b941435f2231749b653484398790
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -36.388281806671955, "std_reward": 28.786278803200254, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-17T00:56:48.968971"}
+{"env_id": "LunarLander-v2", "mean_reward": 70.49066525430779, "std_reward": 43.95125837867714, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-17T22:57:30.390658"}