Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: Deathmatch-v1
     metrics:
     - type: mean_reward
-      value: 57.46 +/- 31.28
+      value: 38.03 +/- 26.60
       name: mean_reward
       verified: false
 ---
@@ -32,11 +32,11 @@ model-index:
 'num_envs': 32
 'num_steps': 128
 'learning_rate': 0.00025
-'learning_rate_min': 1e-05
+'learning_rate_min': 0.0001
 'gamma': 0.99
 'gae_lambda': 0.95
 'clip_coef': None
-'total_timesteps': 30000000
+'total_timesteps': 10000000
 'recurrence': 32
 'ent_coef': 0.001
 'vf_coef': 0.5

logs/events.out.tfevents.1724080638.tf-notebook-0.1425.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebd3572b8e474f32f3c5ca36d40846e1ffb39e4690ed7f5908ffc7a0b6469198
+size 3201176

logs/events.out.tfevents.1724088544.tf-notebook-0.1681.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf390a4ecb8916f5cb3a9a4a740702edba1408c9b622280818de1662cda65f15
+size 42402

logs/events.out.tfevents.1724088663.tf-notebook-0.1941.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78add43d033239048cb4fe9d1930835bf1e7d601692e15ea93feb10b6359ae3c
+size 1302752

logs/events.out.tfevents.1724091878.tf-notebook-0.2195.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a4ada0e0451368b4d90097a203aa5122813392c3ab8832084380b765c807029
+size 2231768

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19b978f0e323a9fcdb279adfdeda0c0b125b3e72c2381d8d69bf3f5c968eb243
-size 16989714
+oid sha256:2a1d2b2f14b3891b6d99f52f5a5b52a7febf3f433a9dc734df4725c95f638ebc
+size 21184018

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae25f894924770b0fc705630e384f69f40e935f651d5b3053b66bed5d98e177a
-size 12578993
+oid sha256:acd398484ac22acf59d16b0b57119d9df44efe796ad2bda53975336ef2150e8e
+size 30007405

results.json

@@ -1 +1 @@
-{"env_id": "Deathmatch-v1", "mean_reward": 57.4557991027832, "std_reward": 31.278539657592773, "n_evaluation_episodes": 10, "eval_datetime": "2024-08-18T21:07:17.534481"}
+{"env_id": "Deathmatch-v1", "mean_reward": 38.02735137939453, "std_reward": 26.600683212280273, "n_evaluation_episodes": 10, "eval_datetime": "2024-08-19T20:06:23.704170"}