Initial Commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: CartPole-v1
     metrics:
     - type: mean_reward
-      value: 83.06 +/- 20.48
+      value: 209.20 +/- 97.11
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 16, "n_training_episodes": 5000, "n_evaluation_episodes": 50, "max_episode_steps": 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_episode_steps": 1000, "gamma": 0.99, "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 sha256:0bc24f14fa0a971176eba4bb34bb9eddfee8dd64fb9609bb4b818ffdf5f534ca
+oid sha256:d1078c03a826dee49368084dad5b728281dc72bbff1d3775d298042aac757c67
 size 3039

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a2ee21dc00e1e62b42d68fc36b3a358fb5c6e9553c9f4c0f6ac4fe46f19418f
-size 3780
+oid sha256:c5162aa23a18bccc38146ca316b92045989ba7d7158338bbba1131095c43ff6d
+size 4786

results.json

@@ -1 +1 @@
-{"env_id": "CartPole-v1", "mean_reward": 83.06, "n_evalauation_episodes": 50, "eval_datetime": "2022-09-03T23:07:30.411019"}
+{"env_id": "CartPole-v1", "mean_reward": 209.2, "n_evalauation_episodes": 50, "eval_datetime": "2022-09-03T23:12:53.119770"}