Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 268.97 +/- 35.91
+      value: -87.46 +/- 35.63
       name: mean_reward
       verified: false
 ---
@@ -37,16 +37,16 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 2000000
+'total_timesteps': 100000
 'learning_rate': 0.00025
-'num_envs': 32
+'num_envs': 128
 'num_steps': 256
 'anneal_lr': True
 'gae': True
 'gamma': 0.99
 'gae_lambda': 0.95
 'num_minibatches': 4
-'update_epochs': 64
+'update_epochs': 32
 'norm_adv': True
 'clip_coef': 0.2
 'clip_vloss': True
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'ahmadsyy/LunarLander-v2_ppo_scratch'
-'batch_size': 8192
-'minibatch_size': 2048}
+'batch_size': 32768
+'minibatch_size': 8192}
   ```
   

logs/events.out.tfevents.1733221076.c20003bcb990.44215.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1e9d33c2c28bd53d04e253d5d1408750039040805a0801d4b4b6c186fe1077e
+size 67897

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6aff11edd6cb849747f1345bc5ea632430b4c7d415bc5ebf764244861624fc4f
+oid sha256:f5d3b8132cd0542fd258c72fe47fd9376c637c45c266b14c60de7d808bf8f676
 size 59774

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 268.96683967903965, "std_reward": 35.9052026725538, "n_evaluation_episodes": 10, "eval_datetime": "2024-12-03T10:13:52.346200"}
+{"env_id": "LunarLander-v2", "mean_reward": -87.45635817623487, "std_reward": 35.632916489774196, "n_evaluation_episodes": 10, "eval_datetime": "2024-12-03T10:18:38.037283"}