Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -106.74 +/- 43.14
+      value: -210.63 +/- 61.02
       name: mean_reward
       verified: false
 ---
@@ -38,9 +38,9 @@ model-index:
 'capture_video': True
 'env_id': 'LunarLander-v2'
 'total_timesteps': 50000
-'learning_rate': 0.007
+'learning_rate': 0.0003
 'num_envs': 16
-'num_steps': 1024
+'num_steps': 1015808
 'anneal_lr': True
 'gae': True
 'gamma': 0.999
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'yaystevek/LunarLander-v2-scratch'
-'batch_size': 16384
-'minibatch_size': 4096}
+'batch_size': 16252928
+'minibatch_size': 4063232}
   ```
   

logs/events.out.tfevents.1693536624.3ba86102856c.14821.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de2f36f9f4fb8e0cf62cee26b20801f99990108bd2414a63e653358ef62479f9
+size 749

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96b74a2201feb6dcf10536ed6baf7008fce337352428a44d8ff9da678ec29cae
+oid sha256:e541b1708d23f31c9369b677df43ff11571f22fa1554ebef621b3cc7dae1051e
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -106.74236945668233, "std_reward": 43.141242979724055, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-01T02:47:11.429020"}
+{"env_id": "LunarLander-v2", "mean_reward": -210.62684050997274, "std_reward": 61.01520799993156, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-01T02:50:31.075128"}