Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 0.62 +/- 1.37
+      value: 0.83 +/- 0.70
       name: mean_reward
       verified: false
 ---
@@ -28,7 +28,7 @@ model-index:
 
   # Hyperparameters
   ```python
-  {'exp_name': 'LunarLanderPPO'
+  {'exp_name': 'LongRunningOriginal'
 'seed': 1
 'torch_deterministic': True
 'cuda': True
@@ -37,16 +37,16 @@ model-index:
 'wandb_entity': None
 'capture_video': True
 'env_id': 'LunarLander-v2'
-'total_timesteps': 200000
-'learning_rate': 0.001
-'num_envs': 4
-'num_steps': 128
-'anneal_lr': True
+'total_timesteps': 4000000
+'learning_rate': 0.00025
+'num_envs': 8
+'num_steps': 1024
+'anneal_lr': False
 'gae': True
 'gamma': 0.999
 'gae_lambda': 0.98
 'num_minibatches': 4
-'update_epochs': 10
+'update_epochs': 4
 'norm_adv': True
 'clip_coef': 0.2
 'clip_vloss': True
@@ -57,7 +57,7 @@ model-index:
 'num_hidden_layers': 2
 'upload_to_hf': True
 'repo_id': 'candrews1971/ppo-LunarLander-v2.1'
-'batch_size': 512
-'minibatch_size': 128}
+'batch_size': 8192
+'minibatch_size': 2048}
   ```
   

logs/events.out.tfevents.1718322924.ChrisGaming.726208.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a625f89d48cec032f8126b0dd60768e65a721899343a1d92818eb96e954ac48
+size 1233549

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc57e79827c84d9474e9ed1ed2bb497f74d8620d31d4f4e91943bea34fe4bafb
+oid sha256:a28348f6869672d4de87040cbef9f4538bbaee7501b85bb2b303fbb89a1b7306
 size 77182

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 0.6173782584307956, "std_reward": 1.3733433744474794, "n_evaluation_episodes": 10, "eval_datetime": "2024-06-13T14:45:17.865722"}
+{"env_id": "LunarLander-v2", "mean_reward": 0.826945648767448, "std_reward": 0.6998308608742364, "n_evaluation_episodes": 10, "eval_datetime": "2024-06-13T19:20:38.468262"}