Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 74.51 +/- 81.01
+      value: 34.28 +/- 42.82
       name: mean_reward
       verified: false
 ---
@@ -42,7 +42,7 @@ model-index:
 'num_envs': 4
 'num_steps': 1024
 'anneal_lr': False
-'gae': True
+'gae': False
 'gamma': 0.9999
 'gae_lambda': 0.95
 'num_minibatches': 4

logs/events.out.tfevents.1712882228.e9e41f7c5b7d.65341.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c23ae9ae5c7b2ef99fe66a99a82f8268fb62193f04218938478893b34c209ca9
+size 1562622

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6930058ac3b7eacf842c60ffd6201b855a3b17b9861775dcedfd7a129a164267
+oid sha256:15cdf2c32f3d1c9ac5340afd4772d544232eb22642ecfd8209afb90adeffcf8f
 size 42898

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 74.50858905844134, "std_reward": 81.00677656870187, "n_evaluation_episodes": 10, "eval_datetime": "2024-04-12T00:27:33.155921"}
+{"env_id": "LunarLander-v2", "mean_reward": 34.28438196628594, "std_reward": 42.82384638510604, "n_evaluation_episodes": 10, "eval_datetime": "2024-04-12T01:18:13.647481"}