Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -250.60 +/- 94.12
+      value: 54.26 +/- 75.11
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 500
+'total_timesteps': 500000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1680452699.86c8819973c5.17891.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cb73c3487219c12a545630a70757af3c1b4d37436e90d7f3885a12ef5441556
+size 503087

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03d9574be091733502dbca67082f02be45fc7d636ea42effe29738297966bd41
+oid sha256:389208e83d3830e2a880958a659b5370f282ed949f20a39702be07d628ebbd32
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -250.59905835162857, "std_reward": 94.12471644877951, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-02T16:16:16.550195"}
+{"env_id": "LunarLander-v2", "mean_reward": 54.255638018631046, "std_reward": 75.11184051824824, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-02T16:39:10.339068"}