Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: CartPole-v1
     metrics:
     - type: mean_reward
-      value: 243.50 +/- 101.55
+      value: 237.20 +/- 134.92
       name: mean_reward
       verified: false
 ---
@@ -28,33 +28,34 @@ model-index:
 
     # Hyperparameters
     ```python
-    {'exp_name': 'unit8_part1'
-'gym_id': 'CartPole-v1'
-'learning_rate': 0.00025
-'seed': 1
-'total_timesteps': 50000
-'torch_deterministic': True
-'cuda': True
-'track': False
-'wandb_project_name': 'ppo-implementation-details'
-'wandb_entity': None
-'capture_video': False
-'num_envs': 4
-'num_steps': 128
-'anneal_lr': True
-'gae': True
-'gamma': 0.99
-'gae_lambda': 0.95
-'num_minibatches': 4
-'update_epochs': 4
-'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': 'tmoroder/ppo-CartPole-v1'
-'batch_size': 512
+    {'exp_name': 'unit8_part1',
+'gym_id': 'CartPole-v1',
+'learning_rate': 0.00025,
+'seed': 1,
+'total_timesteps': 50000,
+'torch_deterministic': True,
+'cuda': True,
+'track': False,
+'wandb_project_name': 'ppo-implementation-details',
+'wandb_entity': None,
+'capture_video': False,
+'num_envs': 4,
+'num_steps': 128,
+'anneal_lr': True,
+'gae': True,
+'gamma': 0.99,
+'gae_lambda': 0.95,
+'num_minibatches': 4,
+'update_epochs': 4,
+'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': 'tmoroder/ppo-CartPole-v1',
+'batch_size': 512,
 'minibatch_size': 128}
-```
+    ```
+    

logs/events.out.tfevents.1741910042.KASHYYYK.31630.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:251759cd358de997aba82057b68b5f44be1d84ce342e43b267e3116cef72b79b
+size 99177

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0e1ac2f4f91febf5e31b6e48719536d769999e7fe7d8b4d60c35209ecdedc61
+oid sha256:eba65fb0eff6563f5ed1e3c8969741418e63bcb8064e2d8bcbe087beb5663774
 size 40466

results.json

@@ -1 +1 @@
-{"env_id": "CartPole-v1", "mean_reward": 243.5, "std_reward": 101.54531008372568, "n_evaluation_episodes": 10, "eval_datetime": "2025-03-14T00:48:09.202069"}
+{"env_id": "CartPole-v1", "mean_reward": 237.2, "std_reward": 134.92056922500734, "n_evaluation_episodes": 10, "eval_datetime": "2025-03-14T00:54:39.231388"}