Push Reinforce agent to the Hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: CartPole-v1
     metrics:
     - type: mean_reward
-      value: 74.80 +/- 13.20
+      value: 500.00 +/- 0.00
       name: mean_reward
       verified: false
 ---

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": 20, "max_t": 2000, "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 sha256:7b536669ab1b7fea4e9d50c97c9459d69c3ebbd5b38f6bf55a70094c34ab0e20
+oid sha256:9b607537751b25e6971fcb9a8df87dbb0b924e54ddd0f215b9fae012e808d7d1
 size 2591

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdffe8c8fb29fb8727b3fc04bc48dfb891697505d91d41ad91ff240562c66e00
-size 8545
+oid sha256:4d1b4b34a592dee3c412a08a39d7d97a64e5509760e72051024f7f7f4479910b
+size 43103

results.json

@@ -1 +1 @@
-{"env_id": "CartPole-v1", "mean_reward": 74.8, "n_evaluation_episodes": 10, "eval_datetime": "2022-09-14T05:15:54.954565"}
+{"env_id": "CartPole-v1", "mean_reward": 500.0, "n_evaluation_episodes": 20, "eval_datetime": "2022-09-14T05:37:15.086079"}