Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -58.55 +/- 95.96
+      value: -147.44 +/- 100.61
       name: mean_reward
       verified: false
 ---
@@ -33,11 +33,11 @@ model-index:
 'torch_deterministic': True
 'cuda': True
 'track': False
-'wandb_project_name': 'cleanRL'
+'wandb_project_name': 'ppoLunarLander'
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 200000
+'total_timesteps': 400000
 'learning_rate': 0.00025
 'num_envs': 16
 'num_steps': 1024
@@ -45,7 +45,7 @@ model-index:
 'gae': True
 'gamma': 0.999
 'gae_lambda': 0.95
-'num_minibatches': 64
+'num_minibatches': 12
 'update_epochs': 4
 'norm_adv': True
 'clip_coef': 0.2
@@ -56,6 +56,6 @@ model-index:
 'target_kl': None
 'repo_id': 'zzen0008/ppo-LunarLander-v2'
 'batch_size': 16384
-'minibatch_size': 256}
+'minibatch_size': 1365}
   ```
   

logs/events.out.tfevents.1678602191.ZZDev.85365.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7aac0e9bba705ebb88622cf94134b6ba6ab22dcde76fa7998ac7a2a864102c47
+size 449971

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf3ee70f04cc02c29a8650e958c3ea6d4cf7e0802b28b9bc524114855183ba8b
+oid sha256:9addb9ea9e42868e9fa6e1be977f052e47a8f797692270ea52ac31b04f092f96
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -58.54703372358121, "std_reward": 95.96058878292462, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-12T17:21:33.729975"}
+{"env_id": "LunarLander-v2", "mean_reward": -147.4378380129283, "std_reward": 100.61164152539268, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-12T17:24:43.120490"}