Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -143.00 +/- 87.22
+      value: -192.49 +/- 112.30
       name: mean_reward
       verified: false
 ---
@@ -38,9 +38,9 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 100000
-'learning_rate': 2e-05
+'learning_rate': 0.0003
 'num_envs': 10
-'num_steps': 128
+'num_steps': 2048
 'anneal_lr': True
 'gae': True
 'gamma': 0.99
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'clemdev2000/ppo2-LunarLander-v2'
-'batch_size': 1280
-'minibatch_size': 320}
+'batch_size': 20480
+'minibatch_size': 5120}
   ```
   

logs/events.out.tfevents.1679138367.0bfcb7fd5bd3.6247.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae3fceb35523b2f98f9b1e9af3fccd63747d2523a06be4195065918ec41fc0e9
+size 105464

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d8976d644bba2e01612cb0079546af3308c8261ac955e4c6b0bc051fecfb74b
+oid sha256:2767e56f26358e76f08e8e26f4d3bb99d4313361ec70ebe6b25a4ddd30523082
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -143.00020129340723, "std_reward": 87.21601832656319, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-18T11:14:14.757367"}
+{"env_id": "LunarLander-v2", "mean_reward": -192.49175212311007, "std_reward": 112.30339322913036, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-18T11:20:01.457100"}