Push Reinforce agent to the Hub

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 197.30 +/- 9.36
+      value: 500.00 +/- 0.00
       name: mean_reward
     task:
       type: reinforcement-learning

hyperparameters.json

@@ -1 +1 @@
-{"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}
+{"h_size": 16, "n_training_episodes": 5000, "n_evaluation_episodes": 50, "max_t": 1000, "gamma": 0.999, "lr": 0.003, "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:e8c9d2877873bb97c71f6d6bde6f0f97682f87da3a72f7a370b127573436ca20
-size 2527
+oid sha256:d340bd0954ec898e8a2513e414b23ce8349658978e562db910d66f4970983087
+size 2719

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73b2f0ffd96281132df56454d2b6418eff2d3aa474b6acc6a250a8ddf0f563c2
-size 17903
+oid sha256:937623ffe9589624e8c032d5a4763417fe3b54ced1bbc31cc06fbe891b11f649
+size 39690

results.json

@@ -1 +1 @@
-{"env_id": "CartPole-v1", "mean_reward": 197.3, "n_evaluation_episodes": 10, "eval_datetime": "2022-07-14T21:27:58.812624"}
+{"env_id": "CartPole-v1", "mean_reward": 500.0, "n_evaluation_episodes": 50, "eval_datetime": "2022-07-15T00:01:27.187457"}