Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -223.69 +/- 89.08
+      value: 22.03 +/- 61.98
       name: mean_reward
       verified: false
 ---
@@ -38,9 +38,9 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 100000
-'learning_rate': 0.0001
+'learning_rate': 0.001
 'num_envs': 4
-'num_steps': 64
+'num_steps': 164
 'anneal_lr': True
 'gae': True
 'gamma': 0.995
@@ -48,14 +48,14 @@ model-index:
 'num_minibatches': 4
 'update_epochs': 4
 'norm_adv': True
-'clip_coef': 0.1
+'clip_coef': 0.2
 'clip_vloss': True
 'ent_coef': 0.01
 'vf_coef': 0.5
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'Marc-Elie/LunarLander-v2-2'
-'batch_size': 256
-'minibatch_size': 64}
+'batch_size': 656
+'minibatch_size': 164}
   ```
   

logs/events.out.tfevents.1684161760.5fc12f631080.25765.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57314f34ba2a79e5e6a952ddea66ab48600cbdf17ea786d7509a5be5cd712529
+size 78794

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb60cd7da7ede9d9f426f84a99dd2c3bec4dfd19a895255c5af662c23ed3d1dc
+oid sha256:eb0dfc264c36fe8b29154facd46fbd3762d42db929e97394b94519842ec9d466
 size 42469

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -223.688422575805, "std_reward": 89.08091002950407, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-15T14:41:43.247211"}
+{"env_id": "LunarLander-v2", "mean_reward": 22.03197476296848, "std_reward": 61.981720157255374, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-15T14:44:55.985532"}