Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: HealthGatheringSupreme-v1
     metrics:
     - type: mean_reward
-      value: 14.87 +/- 10.43
+      value: 1.30 +/- 1.35
       name: mean_reward
       verified: false
 ---
@@ -32,7 +32,7 @@ model-index:
 'learning_rate': 0.0005
 'learning_rate_min': 1e-06
 'gamma': 0.99
-'gae_lambda': 0.99
+'gae_lambda': 0.95
 'clip_coef': 0.2
 'total_timesteps': 2000000
 'recurrence': 16

logs/events.out.tfevents.1722006276.tf-notebook-0.70079.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44d18111e5ebb00030b48c942c576af250f6aa745bce99f0961207e95732986b
+size 710843

logs/events.out.tfevents.1722007068.tf-notebook-0.70242.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cf8761fb98a3c6c71eb609ff19b738947d7011b97a08ccdcf65d008f8621483
+size 88

logs/events.out.tfevents.1722007094.tf-notebook-0.70242.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09d7cc1fd6b3f615d095f854e7e0c38c10780341215e511fb3b659df5d6a4a15
+size 2508

logs/events.out.tfevents.1722007117.tf-notebook-0.70957.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a83c2c91205b289db496ee4cbfc858c1a890cfd2e99f1c7ab8d361a580467c5
+size 88

logs/events.out.tfevents.1722007120.tf-notebook-0.70957.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c393429b50b080fe23c68a0b6a16750f9b071a8cf03f349cddb5d6a4167d856
+size 10395

logs/events.out.tfevents.1722007145.tf-notebook-0.71715.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b4a7f18fa447b94bfa1437e75658f1b0e9e5f019c7f0309c7b16435e3393709
+size 1202971

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5918372a80112df104991af0ffe824801448a7fb544e17dbd2c0c1a71129791d
-size 16108110
+oid sha256:3410880287482100861852f9e0b91772bc87516f7565746423acdbaa3053ef93
+size 13999646

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:492504db6f6e4e6f4360740fb1337fee37392ff67bd4841d8d247e93cb0943fc
-size 62297
+oid sha256:6ff4be59933b0470f4762212f2b8fa32937c713405cbfd57684875d1d88668b5
+size 511695

results.json

@@ -1 +1 @@
-{"env_id": "HealthGatheringSupreme-v1", "mean_reward": 14.868197441101074, "std_reward": 10.425899505615234, "n_evaluation_episodes": 10, "eval_datetime": "2024-07-26T14:20:09.596163"}
+{"env_id": "HealthGatheringSupreme-v1", "mean_reward": 1.3040000200271606, "std_reward": 1.3547334671020508, "n_evaluation_episodes": 10, "eval_datetime": "2024-07-26T15:43:42.239544"}