Push Reinforce agent to the Hub

README.md

@@ -1,6 +1,6 @@
 ---
 tags:
-- CartPole-v1
+- Pixelcopter-PLE-v0
 - reinforce
 - reinforcement-learning
 - custom-implementation
@@ -10,14 +10,14 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 82.70 +/- 13.57
+      value: 8.30 +/- 4.96
       name: mean_reward
     task:
       type: reinforcement-learning
       name: reinforcement-learning
     dataset:
-      name: CartPole-v1
-      type: CartPole-v1
+      name: Pixelcopter-PLE-v0
+      type: Pixelcopter-PLE-v0
 ---
 
   # **Reinforce** Agent playing **CartPole-v1**

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": 64, "n_training_episodes": 50000, "n_evaluation_episodes": 10, "max_t": 10000, "gamma": 0.99, "lr": 0.0001, "env_id": "Pixelcopter-PLE-v0", "state_space": 7, "action_space": 2}

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70e856807d55e145d664fea3e25133f1f0bbd8c20f4165823104476f82b93d6c
-size 2591
+oid sha256:148d852e293a75d1639147e7b902bd945ab7af5c1f5a7096726b47229c8f4429
+size 4703

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5ea14ed4aea5cc08eb7b226686b2f10f0c2983e8f4951221777b1cfa995308e
-size 17173
+oid sha256:d446c138e6c974c8555597947e69cf3baf1891f79c58514603cd88255df34076
+size 6425

results.json

@@ -1 +1 @@
-{"env_id": "CartPole-v1", "mean_reward": 82.7, "n_evaluation_episodes": 10, "eval_datetime": "2022-08-04T07:44:33.152554"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 8.3, "n_evaluation_episodes": 10, "eval_datetime": "2022-08-04T09:09:12.105609"}