Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 38.61 +/- 53.97
+      value: -234.02 +/- 130.10
       name: mean_reward
       verified: false
 ---
@@ -37,8 +37,8 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 400000
-'learning_rate': 0.00025
+'total_timesteps': 10000
+'learning_rate': 0.0005
 'num_envs': 16
 'num_steps': 1024
 'anneal_lr': True

logs/events.out.tfevents.1678606632.ZZDev.109284.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:daafdcd57f055f0e4cd154024073c2837ff98ac84e361e9aef49e98db8044fe7
+size 807

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:040fd673d1bd08aea5eafab4de3077a2004aed0b0f952a14ea3f3b4ef958932c
+oid sha256:ce70ba27206a8224aaecbe977ac744845f603768d9e58d5c9118e616ccb32449
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 38.60630553449567, "std_reward": 53.97355899635028, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-12T17:31:52.888816"}
+{"env_id": "LunarLander-v2", "mean_reward": -234.01879987541216, "std_reward": 130.10059936416008, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-12T18:37:16.025636"}