Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -90.85 +/- 99.38
+      value: -69.13 +/- 64.51
       name: mean_reward
       verified: false
 ---
@@ -38,7 +38,7 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 100000
-'learning_rate': 0.0003
+'learning_rate': 0.0002
 'num_envs': 4
 'num_steps': 2048
 'anneal_lr': True
@@ -48,7 +48,7 @@ model-index:
 'num_minibatches': 32
 'update_epochs': 10
 'norm_adv': True
-'clip_coef': 0.1
+'clip_coef': 0.2
 'clip_vloss': True
 'ent_coef': 0.01
 'vf_coef': 0.25

logs/events.out.tfevents.1679877308.2a0c170730d9.66810.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b352074df68a0f0143f481b751cf4307aa09328eaec544ee263f421a3b0ee5fe
+size 100065

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e33d8bfe623364086eba7c975d8f523c46bfb881245f6696ebb7a647f397e1a
+oid sha256:dba0123b0c3e8c8044da3b3c0a9a49a6d84d3b2afa1424c23d65542b35b4e80a
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -90.8481268785036, "std_reward": 99.37951860354941, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-27T00:34:10.376939"}
+{"env_id": "LunarLander-v2", "mean_reward": -69.12990195762707, "std_reward": 64.50515616992922, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-27T00:36:56.229472"}