Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -133.54 +/- 106.26
+      value: -212.33 +/- 79.08
       name: mean_reward
       verified: false
 ---
@@ -38,7 +38,7 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 50000
-'learning_rate': 0.00025
+'learning_rate': 8e-05
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True

logs/events.out.tfevents.1714947296.71d3fa3d3a00.10860.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b631365b261cc191287a996775bf31a94a45ff8b38e64aa5cfaf5cd01a949eb
+size 108998

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea7adaf29ec4a7754b07ad326b8010d322ac5eb5ac24d758e971d51f95c5895e
+oid sha256:cf33b799dbb26da9c9ef850fc4b4b977abc79c9db1605c0f4535a92481708dcc
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -133.53559910594646, "std_reward": 106.26453066291593, "n_evaluation_episodes": 10, "eval_datetime": "2024-05-05T21:54:18.982587"}
+{"env_id": "LunarLander-v2", "mean_reward": -212.3316276668226, "std_reward": 79.08048582279538, "n_evaluation_episodes": 10, "eval_datetime": "2024-05-05T22:15:41.934296"}