Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -119.94 +/- 120.17
+      value: -18.59 +/- 54.28
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 170000
+'total_timesteps': 200000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1701461810.5051f8bd6bde.15098.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5eec81a33d8b9665665ae3df5097cf4646464a5bcbc41b38175105e42a7d6dc2
+size 356208

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59c1ad256336a830e7e36510df1030d5ff89c138d0c73bccd6ba4d74cb98cb90
+oid sha256:1efdb17a91d165475a33b5df37ed9e8049c65b910cf084fd420eda94a1e63838
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -119.9420012681317, "std_reward": 120.1691073755557, "n_evaluation_episodes": 10, "eval_datetime": "2023-12-01T20:14:31.941310"}
+{"env_id": "LunarLander-v2", "mean_reward": -18.589982149964648, "std_reward": 54.28333661348037, "n_evaluation_episodes": 10, "eval_datetime": "2023-12-01T20:20:14.813209"}