Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -45.00 +/- 35.05
+      value: -168.75 +/- 78.98
       name: mean_reward
       verified: false
 ---
@@ -39,12 +39,12 @@ model-index:
 'env_id': 'LunarLander-v2'
 'total_timesteps': 200000
 'learning_rate': 0.00025
-'num_envs': 4
-'num_steps': 64
+'num_envs': 16
+'num_steps': 1024
 'anneal_lr': True
 'gae': True
-'gamma': 0.98
-'gae_lambda': 0.95
+'gamma': 0.999
+'gae_lambda': 0.98
 'num_minibatches': 4
 'update_epochs': 4
 'norm_adv': True
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'jfelgate/ppo-LunarLander-v2'
-'batch_size': 256
-'minibatch_size': 64}
+'batch_size': 16384
+'minibatch_size': 4096}
   ```
   

logs/events.out.tfevents.1699191745.a8bcc0a3658b.7433.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42119924bd6024aa1d0d0dadd72d865c5a9d4aeeb05af361a8f3b1ac6fc9a68d
+size 248898

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fd917a58798edf4e5c3d70e266fb42dc71dd7d0b0c925ca80f74a235cbaa733
+oid sha256:5702f2b83909dc31a447b9061ed4e18c063d0b6d05ef34ada953045539847f24
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -45.00305117639023, "std_reward": 35.05382057593984, "n_evaluation_episodes": 10, "eval_datetime": "2023-11-05T13:33:05.112102"}
+{"env_id": "LunarLander-v2", "mean_reward": -168.7544216734099, "std_reward": 78.97805679161364, "n_evaluation_episodes": 10, "eval_datetime": "2023-11-05T13:43:27.367163"}