Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -138.83 +/- 95.40
+      value: -235.77 +/- 92.85
       name: mean_reward
       verified: false
 ---
@@ -39,8 +39,8 @@ model-index:
 'env_id': 'LunarLander-v2'
 'total_timesteps': 50000
 'learning_rate': 0.00025
-'num_envs': 4
-'num_steps': 128
+'num_envs': 32
+'num_steps': 512
 'anneal_lr': True
 'gae': True
 'gamma': 0.99
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'igpaub/ppo-LunarLander-v2'
-'batch_size': 512
-'minibatch_size': 128}
+'batch_size': 16384
+'minibatch_size': 4096}
   ```
   

logs/events.out.tfevents.1699614258.e250de559c95.2694.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fed5942ac74abea1a03629db269576016faa5c64d23b3ababb97b91af46c6082
+size 54202

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea7adaf29ec4a7754b07ad326b8010d322ac5eb5ac24d758e971d51f95c5895e
+oid sha256:6aff0bec92ba914a473c7ba793ff26c3a6d112ef9814908acf4c6ea8ca9e5c3a
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -138.8267639947853, "std_reward": 95.40448771953054, "n_evaluation_episodes": 10, "eval_datetime": "2023-11-10T11:02:13.940521"}
+{"env_id": "LunarLander-v2", "mean_reward": -235.76969221500522, "std_reward": 92.85233607012792, "n_evaluation_episodes": 10, "eval_datetime": "2023-11-10T11:04:36.003226"}