Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 113.14 +/- 74.66
+      value: -213.71 +/- 73.95
       name: mean_reward
       verified: false
 ---
@@ -37,10 +37,10 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 1000000
+'total_timesteps': 1000
 'learning_rate': 0.00025
 'num_envs': 4
-'num_steps': 256
+'num_steps': 128
 'anneal_lr': True
 'gae': True
 'gamma': 0.999
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'gstaff/ppo-LunarLander-v2'
-'batch_size': 1024
-'minibatch_size': 256}
+'batch_size': 512
+'minibatch_size': 128}
   ```
   

logs/events.out.tfevents.1677456617.25f188cb86e1.43416.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9604ebd567b10fdb5f13228379e135b580caeb5425860debd12b83780db69358
+size 1553

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54600ebed561f0a38bb5150972e5e097a9df942c066ce89c8ae224d6a351fcc8
+oid sha256:2e75f4b11f55461ced0426e3e88a1f6eeeeae0166ebf8a323ef36bee96c3b54f
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 113.14210202388588, "std_reward": 74.66362305113479, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-26T23:11:16.446200"}
+{"env_id": "LunarLander-v2", "mean_reward": -213.70794756589953, "std_reward": 73.95184436930808, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-27T00:10:23.083066"}