Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -176.63 +/- 87.58
+      value: -41.38 +/- 66.13
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 50000
+'total_timesteps': 100000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1733818110.4adee8f0a652.3812.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b207977bc9794d18f83446546b399bac1a87ba1c46f841fda85a18e6855bf3c
+size 203953

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd4596ab0794d2a541e1ee1543e4c0035dfad1fec7183bccf8aca2cae9fb97b0
+oid sha256:9b4259a04ee11adcc539ffb56970d6e21907eb880b0fc4fc48e9289729dc0389
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -176.63394579868933, "std_reward": 87.5765405248369, "n_evaluation_episodes": 10, "eval_datetime": "2024-12-10T08:05:35.977567"}
+{"env_id": "LunarLander-v2", "mean_reward": -41.37609684821639, "std_reward": 66.13464712043597, "n_evaluation_episodes": 10, "eval_datetime": "2024-12-10T08:09:59.740446"}