Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -108.25 +/- 14.38
+      value: 17.38 +/- 18.63
       name: mean_reward
       verified: false
 ---
@@ -37,11 +37,11 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 1000000
+'total_timesteps': 3000000
 'learning_rate': 0.00025
 'num_envs': 4
-'num_steps': 1024
-'anneal_lr': True
+'num_steps': 2048
+'anneal_lr': False
 'gae': False
 'gamma': 0.9999
 'gae_lambda': 0.98
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'hui168/ppo-LunarLander-v2-from-scratch'
-'batch_size': 4096
-'minibatch_size': 1024}
+'batch_size': 8192
+'minibatch_size': 2048}
   ```
   

logs/events.out.tfevents.1712948134.58af08d562c1.51692.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c01fb2adf9de3e88233a1b22fa2741e49bbe29776e2e3306f5a58f4f1e2e071
+size 2351005

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:762badf8d86dc8ae5ff412913ec7e796c3d423cd0ef74c7e93eb1bdc6c9364c4
+oid sha256:20497ef1b410cb1c533c1f0fb7ec7927970528e0f42af8e3daf2987e4d858550
 size 42898

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -108.24993373513477, "std_reward": 14.378687399809463, "n_evaluation_episodes": 10, "eval_datetime": "2024-04-12T17:55:45.457338"}
+{"env_id": "LunarLander-v2", "mean_reward": 17.382341976694644, "std_reward": 18.63255386028582, "n_evaluation_episodes": 10, "eval_datetime": "2024-04-12T19:52:21.260722"}