Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -28.34 +/- 14.96
+      value: 74.51 +/- 81.01
       name: mean_reward
       verified: false
 ---
@@ -41,9 +41,9 @@ model-index:
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 1024
-'anneal_lr': True
+'anneal_lr': False
 'gae': True
-'gamma': 0.99999
+'gamma': 0.9999
 'gae_lambda': 0.95
 'num_minibatches': 4
 'update_epochs': 4

logs/events.out.tfevents.1712877708.e9e41f7c5b7d.47338.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d87a4371e596d9f651e08fabf70e771b3c0cf8bf77c27af6c4a58e0d944fadd
+size 753277

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ba0033f941b7d0f2b3dbc70518866e65bda85bda2c35db68f57e30563664dc8
+oid sha256:6930058ac3b7eacf842c60ffd6201b855a3b17b9861775dcedfd7a129a164267
 size 42898

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -28.338419955831064, "std_reward": 14.964513522606394, "n_evaluation_episodes": 10, "eval_datetime": "2024-04-11T23:01:44.070491"}
+{"env_id": "LunarLander-v2", "mean_reward": 74.50858905844134, "std_reward": 81.00677656870187, "n_evaluation_episodes": 10, "eval_datetime": "2024-04-12T00:27:33.155921"}