Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -168.12 +/- 69.65
+      value: -32.34 +/- 91.77
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 250000
+'total_timesteps': 1000000
 'learning_rate': 0.0001
 'num_envs': 16
 'num_steps': 1024

logs/events.out.tfevents.1677421290.557f7251d789.17209.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b9b8f25bb0c3d74417e32835932182d5b765681d6d32b935a7d8d60543c3cd9
+size 427985

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc3b30d3f5bacf16f19f0f71a949f90a8ea56ea535883f6ac4dfa73339dc0334
+oid sha256:1553709ecd27456564c1d0ccd8a9de3e60b4e52026dfb56201c42f274936830e
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -168.11844746997775, "std_reward": 69.64875853335595, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-26T14:20:10.935073"}
+{"env_id": "LunarLander-v2", "mean_reward": -32.34374847288065, "std_reward": 91.77280762920067, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-26T14:35:31.099101"}