Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 0.40 +/- 0.99
+      value: 0.62 +/- 1.37
       name: mean_reward
       verified: false
 ---
@@ -37,16 +37,16 @@ model-index:
 'wandb_entity': None
 'capture_video': True
 'env_id': 'LunarLander-v2'
-'total_timesteps': 2000000
-'learning_rate': 0.00025
-'num_envs': 8
-'num_steps': 1024
-'anneal_lr': False
+'total_timesteps': 200000
+'learning_rate': 0.001
+'num_envs': 4
+'num_steps': 128
+'anneal_lr': True
 'gae': True
 'gamma': 0.999
 'gae_lambda': 0.98
 'num_minibatches': 4
-'update_epochs': 4
+'update_epochs': 10
 'norm_adv': True
 'clip_coef': 0.2
 'clip_vloss': True
@@ -55,8 +55,9 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'num_hidden_layers': 2
+'upload_to_hf': True
 'repo_id': 'candrews1971/ppo-LunarLander-v2.1'
-'batch_size': 8192
-'minibatch_size': 2048}
+'batch_size': 512
+'minibatch_size': 128}
   ```
   

logs/events.out.tfevents.1718311163.ChrisGaming.637147.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d66ddeacb0ac17c0bcb2e0859a1653a6fe05cc7ab790c999e4b710058f71cb0
+size 276763

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b717fec2791bbcfd67e14ea159dba8b0b0f81437b5746b5ae6dd43227c83b789
+oid sha256:bc57e79827c84d9474e9ed1ed2bb497f74d8620d31d4f4e91943bea34fe4bafb
 size 77182

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 0.39733913276566374, "std_reward": 0.9932994239311711, "n_evaluation_episodes": 10, "eval_datetime": "2024-06-13T13:42:23.492494"}
+{"env_id": "LunarLander-v2", "mean_reward": 0.6173782584307956, "std_reward": 1.3733433744474794, "n_evaluation_episodes": 10, "eval_datetime": "2024-06-13T14:45:17.865722"}