Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -163.36 +/- 112.06
+      value: -41.61 +/- 54.89
       name: mean_reward
       verified: false
 ---
@@ -43,12 +43,12 @@ model-index:
 'num_steps': 1000
 'anneal_lr': True
 'gae': True
-'gamma': 0.99
-'gae_lambda': 0.95
+'gamma': 0.999
+'gae_lambda': 0.98
 'num_minibatches': 128
-'update_epochs': 1
+'update_epochs': 2
 'norm_adv': True
-'clip_coef': 0.01
+'clip_coef': 0.05
 'clip_vloss': True
 'ent_coef': 0.01
 'vf_coef': 0.05

logs/events.out.tfevents.1711130024.tikhon-XPS-15-9570.19393.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c62f516a555c7bac6751a6724022e9cd5610403228e1cef49481d2c243ec8da
+size 913019

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b94d3737a6ab5f657f18ad5f43f1c422091b1483a807f937e90d99640922745f
+oid sha256:2b248444741e0ff0e9d4dfcfe64510407e0298e2520ba8309ae9f5c0f020bad2
 size 80274

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -163.35542639494165, "std_reward": 112.0595510405238, "n_evaluation_episodes": 10, "eval_datetime": "2024-03-22T20:40:11.357832"}
+{"env_id": "LunarLander-v2", "mean_reward": -41.60905722808679, "std_reward": 54.89427414950447, "n_evaluation_episodes": 10, "eval_datetime": "2024-03-22T20:59:42.480240"}