Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 106.07 +/- 53.15
+      value: 123.45 +/- 107.21
       name: mean_reward
       verified: false
 ---
@@ -37,10 +37,10 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 1000000
+'total_timesteps': 2000000
 'learning_rate': 0.00025
 'num_envs': 4
-'num_steps': 512
+'num_steps': 128
 'anneal_lr': True
 'gae': True
 'gamma': 0.999
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'gstaff/ppo-LunarLander-v2'
-'batch_size': 2048
-'minibatch_size': 512}
+'batch_size': 512
+'minibatch_size': 128}
   ```
   

logs/events.out.tfevents.1677459674.25f188cb86e1.56344.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b1c45cb9fff24f24c8e6aa1c8925d1e241b2558667511ff095e7d2898ba614d
+size 2735619

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae0d6aa21e271da69955977a6403945a3d8a221472f1f4163801d505f7fb9ccf
+oid sha256:1646a5c04d2471ad20d041870ca00bed0cf58308ad7583208ea9265ab32c91cd
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 106.0703485949823, "std_reward": 53.145236412589945, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-27T00:59:49.106318"}
+{"env_id": "LunarLander-v2", "mean_reward": 123.45184778060676, "std_reward": 107.2148313402014, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-27T01:41:11.260196"}