Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -174.72 +/- 104.98
+      value: -75.41 +/- 84.31
       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.1683997907.c6e3bac58bc0.3182.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d98b6fad549efcc272074cb0507ca2118c045fe27b8022e91317f5fefeeb42bc
+size 1255653

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e304481d929ee4afe57bfc2f353b7139b5b63a076ea2edd03f0735d5bc715ad
+oid sha256:40b5ee98fe5b77f599f75eced20a5c68d36ddeea5a4e95056c913a979871babc
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -174.72126576929514, "std_reward": 104.98023083176598, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-13T17:11:02.005627"}
+{"env_id": "LunarLander-v2", "mean_reward": -75.40532175383694, "std_reward": 84.31239048651376, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-13T17:46:15.235422"}