Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -222.96 +/- 120.51
+      value: -171.14 +/- 110.68
       name: mean_reward
       verified: false
 ---
@@ -44,7 +44,7 @@ model-index:
 'num_steps': 1024
 'anneal_lr': True
 'gae': True
-'gamma': 0.1
+'gamma': 0.05
 'gae_lambda': 0.98
 'num_minibatches': 4
 'update_epochs': 4

logs/events.out.tfevents.1694599145.422f4b7e0f84.15609.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04e564a027dbfc5510f378c2d9ba108fce432d45f68d6eed797ae293e5b9a7f6
+size 107274

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7880036abd2942bd09593a88fadef93d1a3f8aa72ca53912e82f04d067b2afe7
+oid sha256:fe22d04cd9cf73fea23210db18744aa7c37b8433dbe76dc176354ad0791c8576
 size 42469

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -222.95883281534617, "std_reward": 120.50891227216498, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-13T09:56:53.943301"}
+{"env_id": "LunarLander-v2", "mean_reward": -171.13956495562184, "std_reward": 110.67936200171252, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-13T10:00:06.704991"}