Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -43.50 +/- 83.15
+      value: -43.48 +/- 111.28
       name: mean_reward
       verified: false
 ---
@@ -43,12 +43,12 @@ model-index:
 'num_steps': 128
 'anneal_lr': True
 'gae': True
-'gamma': 0.95
+'gamma': 0.93
 'gae_lambda': 0.9
 'num_minibatches': 4
 'update_epochs': 8
 'norm_adv': True
-'clip_coef': 0.1
+'clip_coef': 0.15
 'clip_vloss': True
 'ent_coef': 0.01
 'vf_coef': 0.5

logs/events.out.tfevents.1698454857.5d0621e95616.44924.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3907f38b9b0399a97572412509aef535a543a9201be65e3ea872250ec7d9adc8
+size 150953

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:416bfcd6e77b044f9d7a96ea58b330ec5f2efa50d00eb772db8a4fd52d1f5879
+oid sha256:6fb16e6d421e6fe246524a21f0390efe4ad92bb3849fbc981c475b042b292d07
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -43.50096169058103, "std_reward": 83.15334937844422, "n_evaluation_episodes": 10, "eval_datetime": "2023-10-28T00:58:53.624454"}
+{"env_id": "LunarLander-v2", "mean_reward": -43.47633660868862, "std_reward": 111.27950451353276, "n_evaluation_episodes": 10, "eval_datetime": "2023-10-28T01:03:25.307116"}