Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -139.06 +/- 52.78
+      value: -128.06 +/- 57.14
       name: mean_reward
       verified: false
 ---
@@ -48,11 +48,11 @@ model-index:
 'num_minibatches': 4
 'update_epochs': 4
 'norm_adv': True
-'clip_coef': 0.2
+'clip_coef': 0.1
 'clip_vloss': True
 'ent_coef': 0.01
 'vf_coef': 0.5
-'max_grad_norm': 0.5
+'max_grad_norm': 0.4
 'target_kl': None
 'repo_id': 'robotman0/ppo-LunarLander-v2'
 'batch_size': 512

logs/events.out.tfevents.1677255982.48ea9199715b.6245.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:866292d26067297fd57151be27e816e4a3731f3cdd925de39d2aa8bde2abd34b
+size 110558

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3262cb9f8d71762568958150de91d2adbb7385c87e56d48030e8005230aa5d95
+oid sha256:9df7df9211be735650c367e8a66fa8ffad034369f609addd046e734b0a32d4ea
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -139.0576725645491, "std_reward": 52.78203348377827, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-24T16:22:36.715739"}
+{"env_id": "LunarLander-v2", "mean_reward": -128.06150100249698, "std_reward": 57.1361883217084, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-24T16:27:07.442650"}