Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -179.78 +/- 154.45
+      value: -18.53 +/- 54.84
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 45000
+'total_timesteps': 120000
 'learning_rate': 0.0003
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1676762181.c16ce66bfd21.2246.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24ac7313b3a0ff225a6666f36e20e1ffd79945c0e62ac764e4c73dc74da72817
+size 215084

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b57842bb6212b6cc2f58a07696226ff7ee66650cbc3119e3ca05853b714d8bb0
-size 142801
+oid sha256:ddb3044ac0faa1763fff137efa9d3d725ebb7fbe9292747afe1df734b39af82d
+size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -179.77814168237052, "std_reward": 154.4457817373032, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-18T22:14:54.498923"}
+{"env_id": "LunarLander-v2", "mean_reward": -18.53090300466866, "std_reward": 54.836841387166245, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-18T23:18:33.433704"}