Push Reinforce agent to the Hub

README.md

@@ -11,7 +11,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: -138.17 +/- 94.17
+      value: 103.08 +/- 43.38
       name: mean_reward
     task:
       type: reinforcement-learning
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 50000
+'total_timesteps': 500000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1659741186.005638f23f8c.833.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05ea0a39c8089de0af52f3367bf298e6ec82766b1d6add81ad7b67028b456138
+size 656258

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:633f99a5be1425b9bb78acedbd8f155afa914e7550ea09f7eacf5e08d615cfba
+oid sha256:d533664311d019bac32c039bc8afe737ab3c75c6178d8082cf6a77e92acc86a0
 size 42817

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -138.16997918081066, "std_reward": 94.16888020946013, "n_evaluation_episodes": 10, "eval_datetime": "2022-08-05T23:11:46.583161"}
+{"env_id": "LunarLander-v2", "mean_reward": 103.07583089813492, "std_reward": 43.37872462393049, "n_evaluation_episodes": 10, "eval_datetime": "2022-08-05T23:27:38.046826"}