Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: HealthGatheringSupreme-v1
     metrics:
     - type: mean_reward
-      value: 1.30 +/- 1.35
+      value: 0.57 +/- 0.78
       name: mean_reward
       verified: false
 ---
@@ -38,7 +38,7 @@ model-index:
 'recurrence': 16
 'ent_coef': 0.001
 'vf_coef': 0.5
-'max_grad_norm': 4.0
+'max_grad_norm': 10000
 'epsilon': 0
 'num_minibatches': 1
 'update_epochs': 1

logs/events.out.tfevents.1722008796.tf-notebook-0.72310.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a5943e608d66d8ffb687919cb19e641d69b9f8bd8fe5d5822f43e3450ec9fc1
+size 1202971

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3410880287482100861852f9e0b91772bc87516f7565746423acdbaa3053ef93
+oid sha256:0928c8e1c60f15f02aef350a68d73b5aa3b68a19757a5aae57af9416cf5811f1
 size 13999646

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ff4be59933b0470f4762212f2b8fa32937c713405cbfd57684875d1d88668b5
-size 511695
+oid sha256:8e08ad69722705e7522e8cb79dda9af2f6d7a896f52453db086b3fd6b7ea4cb8
+size 435975

results.json

@@ -1 +1 @@
-{"env_id": "HealthGatheringSupreme-v1", "mean_reward": 1.3040000200271606, "std_reward": 1.3547334671020508, "n_evaluation_episodes": 10, "eval_datetime": "2024-07-26T15:43:42.239544"}
+{"env_id": "HealthGatheringSupreme-v1", "mean_reward": 0.5699999928474426, "std_reward": 0.7751525044441223, "n_evaluation_episodes": 10, "eval_datetime": "2024-07-26T16:08:16.416116"}