Push Reinforce agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -109.84 +/- 31.53
+      value: -182.85 +/- 149.99
       name: mean_reward
       verified: false
 ---
@@ -38,7 +38,7 @@ 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.1675381973.lokman-system76-pc.414992.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed4d6a94dc5acea60563940eaea554ae9f06f2961203ec55fc6df5ae49ce748a
+size 219173

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aae709a8c9b664ec036f6cee0e61b370dc07756e22a19c1839201aca04b1f527
+oid sha256:e917b943abb76584ef0538250a880892a32f25155ae73152713cbf3f2b6ae40a
 size 42817

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -109.8428858931629, "std_reward": 31.528056324717806, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-02T15:50:49.993110"}
+{"env_id": "LunarLander-v2", "mean_reward": -182.85257232790173, "std_reward": 149.9949660371247, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-02T15:54:03.174351"}