Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -63.82 +/- 61.20
+      value: -8.42 +/- 33.15
       name: mean_reward
       verified: false
 ---
@@ -40,7 +40,7 @@ model-index:
 'total_timesteps': 200000
 'learning_rate': 0.00025
 'num_envs': 4
-'num_steps': 128
+'num_steps': 64
 'anneal_lr': True
 'gae': True
 'gamma': 0.98
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'jfelgate/ppo-LunarLander-v2'
-'batch_size': 512
-'minibatch_size': 128}
+'batch_size': 256
+'minibatch_size': 64}
   ```
   

logs/events.out.tfevents.1698073279.527fe3665085.28050.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a46d9a67cd903fb3b511aa2f2eb83feb55d5793813b7fede83c2251201beb11e
+size 482784

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8efa7dc03824403a87d331a1629d4c059898e96ef654d2868f2c42a94632f69
+oid sha256:af0278543cc04ab9de0c1d476f447c31601a467ba265094f235f2978193656cd
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -63.81700733366519, "std_reward": 61.19662367355915, "n_evaluation_episodes": 10, "eval_datetime": "2023-10-23T14:59:52.442044"}
+{"env_id": "LunarLander-v2", "mean_reward": -8.418234843777473, "std_reward": 33.14746696720495, "n_evaluation_episodes": 10, "eval_datetime": "2023-10-23T15:07:58.105395"}