Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -131.44 +/- 59.79
+      value: -81.26 +/- 71.22
       name: mean_reward
       verified: false
 ---
@@ -40,7 +40,7 @@ model-index:
 'total_timesteps': 100000
 'learning_rate': 0.0001
 'num_envs': 4
-'num_steps': 1024
+'num_steps': 256
 'anneal_lr': True
 'gae': True
 'gamma': 0.99
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'slava-medvedev/unit8-ppo-LunarLander-v2'
-'batch_size': 4096
-'minibatch_size': 256}
+'batch_size': 1024
+'minibatch_size': 64}
   ```
   

logs/events.out.tfevents.1698341971.e81c8261624b.8641.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5605eae1c6f92f267f8d55faf6817987b1c00b17e63d440d19212e26574cc34
+size 150182

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:183fc86459f936728dfa1a06eae1496110f4a7fc02d4aface727c685c7dcdd8f
+oid sha256:847376341ed258bba1e32f851a9721e98c0cfda74f09797be6cce92d3b57a5b2
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -131.44013028093292, "std_reward": 59.79377215983551, "n_evaluation_episodes": 10, "eval_datetime": "2023-10-26T17:39:01.347514"}
+{"env_id": "LunarLander-v2", "mean_reward": -81.25575369404757, "std_reward": 71.22034112908497, "n_evaluation_episodes": 10, "eval_datetime": "2023-10-26T17:41:41.259702"}