Push Reinforce agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -162.88 +/- 78.93
+      value: -158.01 +/- 38.12
       name: mean_reward
       verified: false
 ---
@@ -38,7 +38,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 1000000
+'total_timesteps': 100000
 'learning_rate': 0.000125
 'num_envs': 16
 'num_steps': 256

logs/events.out.tfevents.1662324891.624f3f3c0672.770.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e191235869916ee81b3f5f94ece51fa3a427e01f4e74c9e39875cd2ba01028dc
+size 13013

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06deccbb7adc999536f3496e49815e9b1fad596f4988072376b1b7a751894178
+oid sha256:f3620316316206e30f94908b79f24d4d44a5cd8bddd109b78046e447f1fc0bf2
 size 42689

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -162.88328449226753, "std_reward": 78.92687312975224, "n_evaluation_episodes": 10, "eval_datetime": "2022-09-04T20:52:40.675612"}
+{"env_id": "LunarLander-v2", "mean_reward": -158.00572748657743, "std_reward": 38.122258531643375, "n_evaluation_episodes": 10, "eval_datetime": "2022-09-04T20:55:26.211208"}