Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -69.44 +/- 19.10
+      value: -108.39 +/- 38.54
       name: mean_reward
       verified: false
 ---
@@ -38,12 +38,12 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 140000
-'learning_rate': 0.0005
+'learning_rate': 0.00025
 'num_envs': 4
-'num_steps': 128
+'num_steps': 256
 'anneal_lr': True
 'gae': True
-'gamma': 0.99
+'gamma': 0.999
 'gae_lambda': 0.95
 'num_minibatches': 4
 'update_epochs': 4
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'VAZaytsev/ppo_LL_v2'
-'batch_size': 512
-'minibatch_size': 128}
+'batch_size': 1024
+'minibatch_size': 256}
   ```
   

logs/events.out.tfevents.1678632372.d093eede9204.10275.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:076e8ba8c29d5d9d5406f8e4da693be99843cd9f58447cffa349bb580bcf0c11
+size 236037

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:865fc3ad2f7dd1233e7d58b5ab9ccd6dc4b29612bc680221b22b3070b100e491
+oid sha256:101de066839d7d9efafa5f892541d84af5fb7c642db859955a6d1ca3a86edce4
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -69.43978216106034, "std_reward": 19.096080902547197, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-12T14:40:20.924838"}
+{"env_id": "LunarLander-v2", "mean_reward": -108.39468923397155, "std_reward": 38.54251020300454, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-12T14:48:03.405933"}