Push agent to the Hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+replay.mp4 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -114.94 +/- 59.13
+      value: -96.96 +/- 38.30
       name: mean_reward
       verified: false
 ---
@@ -27,35 +27,4 @@ model-index:
   This is a trained model of a PPO agent playing LunarLander-v2.
 
   # Hyperparameters
-  ```python
-  {'exp_name': 'ppo'
-'seed': 1
-'torch_deterministic': True
-'cuda': True
-'track': False
-'wandb_project_name': 'cleanRL'
-'wandb_entity': None
-'capture_video': False
-'env_id': 'LunarLander-v2'
-'total_timesteps': 100000
-'learning_rate': 0.0003
-'num_envs': 4
-'num_steps': 2048
-'anneal_lr': True
-'gae': True
-'gamma': 0.99
-'gae_lambda': 0.98
-'num_minibatches': 4
-'update_epochs': 10
-'norm_adv': True
-'clip_coef': 0.2
-'clip_vloss': True
-'ent_coef': 0.01
-'vf_coef': 0.5
-'max_grad_norm': 0.5
-'target_kl': None
-'repo_id': 'sighmon/ppo-cleanrl-LunarLander-v2'
-'batch_size': 8192
-'minibatch_size': 2048}
-  ```
   

logs/events.out.tfevents.1740799768.simosx.local.58483.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87e3a7b64fe85c62707849e9fa6a1bdb098b769c6e90a10e10faafdb88047284
+size 1223160

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78186996c7f969478564b1bddbed754efcbbd2f0fc2ef92ad1b43ea3e299897d
-size 43026
+oid sha256:13b576762c17bcf5ac5d48c63c93b560f35da88344a8e82e0b0a3fb12ed04866
+size 42898

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:005b7c3318a5209ecda0aaec2c383ed09200019f4246d960ab1564326246ab12
+size 211713

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -114.93977400071144, "std_reward": 59.13364114336735, "n_evaluation_episodes": 10, "eval_datetime": "2025-03-01T01:54:44.669021"}
+{"env_id": "LunarLander-v2", "mean_reward": -96.9561269505989, "std_reward": 38.30065452721645, "n_evaluation_episodes": 10, "eval_datetime": "2025-03-01T14:19:48.771164"}