Push Reinforce agent to the Hub

README.md

@@ -1,6 +1,6 @@
 ---
 tags:
-- Pong-PLE-v0
+- CartPole-v1
 - reinforce
 - reinforcement-learning
 - custom-implementation
@@ -10,14 +10,14 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: -16.00 +/- 0.00
+      value: 70.60 +/- 24.99
       name: mean_reward
     task:
       type: reinforcement-learning
       name: reinforcement-learning
     dataset:
-      name: Pong-PLE-v0
-      type: Pong-PLE-v0
+      name: CartPole-v1
+      type: CartPole-v1
 ---
 
   # **Reinforce** Agent playing **CartPole-v1**

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 64, "n_training_episodes": 20000, "n_evaluation_episodes": 10, "max_t": 5000, "gamma": 0.99, "lr": 0.01, "env_id": "Pong-PLE-v0", "state_space": 7, "action_space": 3}
+{"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}

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b479939af67bdb0710224055c1d282484b01b9e25677a583ccccd6febc182eac
-size 39511
+oid sha256:f1693c3289cc3f3afbb39619ca778cdcc2bd774abed8dd9fd474a454066ddba0
+size 2591

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37f5ae2c7849548a38eb649dbd0680b90ba2f70483e4fb2c9019258f2967f651
-size 13585
+oid sha256:f5f6198e78f15ef533c9b87d7f4aa302f8c8989f4d025f45c5462a7bbb0303a6
+size 10432

results.json

@@ -1 +1 @@
-{"env_id": "Pong-PLE-v0", "mean_reward": -16.0, "n_evaluation_episodes": 10, "eval_datetime": "2022-08-09T15:05:27.991118"}
+{"env_id": "CartPole-v1", "mean_reward": 70.6, "n_evaluation_episodes": 10, "eval_datetime": "2022-08-10T15:31:40.756290"}