Push Reinforce agent to the Hub

README.md

@@ -1,6 +1,6 @@
 ---
 tags:
-- Pixelcopter-PLE-v0
+- Pong-PLE-v0
 - reinforce
 - reinforcement-learning
 - custom-implementation
@@ -10,14 +10,14 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 14.20 +/- 14.13
+      value: -16.00 +/- 0.00
       name: mean_reward
     task:
       type: reinforcement-learning
       name: reinforcement-learning
     dataset:
-      name: Pixelcopter-PLE-v0
-      type: Pixelcopter-PLE-v0
+      name: Pong-PLE-v0
+      type: Pong-PLE-v0
 ---
 
   # **Reinforce** Agent playing **CartPole-v1**

hyperparameters.json

@@ -1 +1 @@
-{"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}
+{"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}

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7c69af623b0f6dd157713245f4e40a878df1c8e6ee5ad6ea4807b9b83fe0112
-size 4703
+oid sha256:b479939af67bdb0710224055c1d282484b01b9e25677a583ccccd6febc182eac
+size 39511

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52a24857724da538a62816837a91e10323138b7ff9d1fbb5a0f58ce29c219551
-size 9769
+oid sha256:37f5ae2c7849548a38eb649dbd0680b90ba2f70483e4fb2c9019258f2967f651
+size 13585

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 14.2, "n_evaluation_episodes": 10, "eval_datetime": "2022-08-09T12:50:49.427113"}
+{"env_id": "Pong-PLE-v0", "mean_reward": -16.0, "n_evaluation_episodes": 10, "eval_datetime": "2022-08-09T15:05:27.991118"}