Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 206.79 +/- 44.12
+      value: 180.87 +/- 87.15
       name: mean_reward
       verified: false
 ---
@@ -41,7 +41,7 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'num_envs': 4
-'num_steps': 128
+'num_steps': 64
 'anneal_lr': True
 'gae': True
 'gamma': 0.999
@@ -56,7 +56,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'FredericProtat/ppo-LunarLander-v2'
-'batch_size': 512
-'minibatch_size': 128}
+'batch_size': 256
+'minibatch_size': 64}
   ```
   

logs/events.out.tfevents.1694623598.b693a32d7521.21677.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ff2e407f3da56aa3a8fa3c967ba53e027efe9ee2d447d1379d8de37abe78d82
+size 2360785

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:908ef76cf88a369f92d86a0bb41b65ce2195b1568925020d9154479af2077526
+oid sha256:8fde319b199e6ba206e29341023901e81f0fb5821518358972095840df2b6dab
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 206.7885925496649, "std_reward": 44.119986871062686, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-13T16:37:15.917877"}
+{"env_id": "LunarLander-v2", "mean_reward": 180.87030309405972, "std_reward": 87.15365519050508, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-13T17:09:17.552138"}