Push Reinforce agent to the Hub

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 120.80 +/- 40.22
+      value: 273.60 +/- 40.64
       name: mean_reward
     task:
       type: reinforcement-learning

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 16, "n_training_episodes": 1000, "n_evaluation_episodes": 10, "max_t": 1000, "gamma": 1.0, "lr": 0.01, "env_id": "CartPole-v1", "state_space": 4, "action_space": 2}
+{"h_size": 16, "n_training_episodes": 10000, "n_evaluation_episodes": 10, "max_t": 1000, "gamma": 1.0, "lr": 0.01, "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 sha256:28c4f9db4ac6b39491846529499dddf02598282168452ca6123cf320e7488f3f
+oid sha256:5d76b06b53f8651eb5ea2b21c689b92b4dfcfb730d48c8b87749e9dc4608d333
 size 2655

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40e887ec62224bee1560aad82c8ee3a3d56c511832dd2dd8013d7ceb73d8b599
-size 13933
+oid sha256:77c0e02ab03944ba8aca5ea4d2049ca2a57915d11635ce423d96bfd353a0c1e0
+size 32307

results.json

@@ -1 +1 @@
-{"env_id": "CartPole-v1", "mean_reward": 120.8, "n_evaluation_episodes": 10, "eval_datetime": "2022-07-05T00:39:39.430137"}
+{"env_id": "CartPole-v1", "mean_reward": 273.6, "n_evaluation_episodes": 10, "eval_datetime": "2022-07-05T01:27:39.189623"}