Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -189.04 +/- 97.50
+      value: -3.73 +/- 113.17
       name: mean_reward
       verified: false
 ---
@@ -37,10 +37,10 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 50000
+'total_timesteps': 5000000
 'learning_rate': 0.00025
-'num_envs': 4
-'num_steps': 128
+'num_envs': 8
+'num_steps': 258
 'anneal_lr': True
 'gae': True
 'gamma': 0.99
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'EvaOr/chp8-ppo-LunarLander-v2-UNDERSTANDED'
-'batch_size': 512
-'minibatch_size': 128}
+'batch_size': 2064
+'minibatch_size': 516}
   ```
   

logs/events.out.tfevents.1680607581.591ba12882cd.7364.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bc04cd2b04071988e0c537b3f7a5666a14e3016bd6ece3e5c258214438ba44d
+size 1260670

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:352b29f3c3f4d4e2a36b5743be7dd26cde2d9e8abe40e72c375dcb319e6f5ecc
+oid sha256:aea41728234084392599854ae00aa8378703e8871711eb03c851d77cf4119d2a
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -189.04350419874638, "std_reward": 97.502012765183, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-04T11:21:53.631928"}
+{"env_id": "LunarLander-v2", "mean_reward": -3.734516118187075, "std_reward": 113.1737440998333, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-04T13:13:53.073707"}