Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -139.21 +/- 63.29
+      value: -60.01 +/- 41.72
       name: mean_reward
       verified: false
 ---
@@ -37,13 +37,13 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 100000
+'total_timesteps': 2000000
 'learning_rate': 0.00025
 'num_envs': 4
-'num_steps': 128
+'num_steps': 4000
 'anneal_lr': True
 'gae': True
-'gamma': 0.998
+'gamma': 0.999
 'gae_lambda': 0.98
 'num_minibatches': 4
 'update_epochs': 4
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'AndrewL088/ppo-Luna-v2'
-'batch_size': 512
-'minibatch_size': 128}
+'batch_size': 16000
+'minibatch_size': 4000}
   ```
   

logs/events.out.tfevents.1694927918.ee290f883918.14020.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b714346c961b9e35704c09ba7128d50a15051b18280b65db4a3359443165392
+size 1956627

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83877babb22ce07030b2c37c1791e8a1da8ec0361751252f14855424bc98a3db
+oid sha256:950c48532e8a76b4c5fdac176fad3e9e796f092a610a646608c6f33b795ecf6a
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -139.20895931667923, "std_reward": 63.2928091476428, "n_evaluation_episodes": 20, "eval_datetime": "2023-09-17T05:08:13.941384"}
+{"env_id": "LunarLander-v2", "mean_reward": -60.00557580971008, "std_reward": 41.721458045074385, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-17T05:41:50.098713"}