Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -150.99 +/- 82.82
+      value: -160.58 +/- 103.91
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 5000
+'total_timesteps': 50000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128
@@ -54,6 +54,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'toinsson/ppo-cartpole-v0'
+'huggingface_token': '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'
 'batch_size': 512
 'minibatch_size': 128}
     ```

logs/events.out.tfevents.1677323790.ba5d71ca044b.1.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4647eff6fd28e1492aef76c58e55b4aac6aff8c16232a99c7afbd50d548a049a
+size 111259

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2369e1285ed448a75cfcbaabb04b05f0113a6687ac1bb65fce3daad51a84f274
+oid sha256:61e239b14468c3d6f57613895d9fa7a8c8f67ebe854e8af13477bfbd5e8612d8
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -150.98777663868825, "std_reward": 82.81671505549093, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-24T19:22:26.367788"}
+{"env_id": "LunarLander-v2", "mean_reward": -160.58220473118587, "std_reward": 103.91426731661545, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-25T15:16:57.562898"}