Push Reinforce agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -161.62 +/- 108.46
+      value: -26.60 +/- 97.28
       name: mean_reward
       verified: false
 ---
@@ -33,7 +33,7 @@ model-index:
 'env_id': 'LunarLander-v2'
 'learning_rate': 0.00025
 'seed': 1
-'total_timesteps': 50000
+'total_timesteps': 1000000
 'torch_deterministic': True
 'cuda': True
 'track': False

logs/events.out.tfevents.1681508559.2c4a36324d05.13401.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:070ece9dd59a2c2908bef65fd4e0ca01fb8cc3d503601d44580e9baaf71dae81
+size 889115

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdcf78178ab033a93b34f7326d70cc42208f7483f1f35803a03aad5050e0f842
+oid sha256:4abef1596f159d487d84d675dac8f49da48d0ac270d805d5c39bfc2c3e9f9286
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -161.6151118749849, "std_reward": 108.45528836412366, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-14T21:40:36.646050"}
+{"env_id": "LunarLander-v2", "mean_reward": -26.595498871538098, "std_reward": 97.28255688863723, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-14T22:10:33.819737"}