Push Reinforce agent to the Hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: CartPole-v1
     metrics:
     - type: mean_reward
-      value: 155.80 +/- 32.34
+      value: 157.60 +/- 28.70
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 64, "n_training_episodes": 5000, "n_evaluation_episodes": 10, "max_t": 5000, "gamma": 0.98, "lr": 0.001, "env_id": "CartPole-v1", "state_space": 4, "action_space": 2}
+{"h_size": 64, "n_training_episodes": 5000, "n_evaluation_episodes": 10, "max_t": 10000, "gamma": 0.98, "lr": 0.001, "env_id": "CartPole-v1", "state_space": 4, "action_space": 2}

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:352469c1f9cab5c037afaddca23d5172c98504ecf0f658f66285e3103bccc73f
+oid sha256:8d32853245589aae5406349dde1f79c1a866fc514115430041a5359c4eb43786
 size 3935

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8d8126f130291328ce8a1aebfa53b7a5d4ee0d3e33766e7b0489e58c19b9326
-size 18024
+oid sha256:c477725f06f74971d71cad5b3dd72b3b0d19ec5798a47fc00d32db83fd0b841f
+size 23708

results.json

@@ -1 +1 @@
-{"env_id": "CartPole-v1", "mean_reward": 155.8, "n_evaluation_episodes": 10, "eval_datetime": "2022-12-03T13:29:57.713674"}
+{"env_id": "CartPole-v1", "mean_reward": 157.6, "n_evaluation_episodes": 10, "eval_datetime": "2022-12-03T13:38:19.120134"}