Upload folder using huggingface_hub

.gitattributes

@@ -25,7 +25,6 @@
 *.safetensors filter=lfs diff=lfs merge=lfs -text
 saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
 *.tflite filter=lfs diff=lfs merge=lfs -text
 *.tgz filter=lfs diff=lfs merge=lfs -text
 *.wasm filter=lfs diff=lfs merge=lfs -text

README.md

@@ -6,7 +6,7 @@ tags:
 - custom-implementation
 - deep-rl-class
 model-index:
-- name: Reinforce-Pixelcopter-PLE-v0
+- name: Reinforce-version2
   results:
   - task:
       type: reinforcement-learning
@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 249.80 +/- 178.58
+      value: 74.20 +/- 42.22
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 64, "n_training_episodes": 9000, "n_evaluation_episodes": 10, "max_t": 200000, "gamma": 0.99, "lr": 0.0001, "env_id": "Pixelcopter-PLE-v0", "state_space": 7, "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 sha256:2a8c808c15b207ba6064d3aed4fda2aa1bc72b17db857d72a2c3fb9f8046f44f
-size 39239
+oid sha256:15fadcd60501a3784d81ceb60d83af4019defc15865619e944e8c4ce168af07d
+size 38983

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c06529438853ca529fb8fab4830708a5ef443200898775ddefccef3034f69d98
-size 405194
+oid sha256:093f5f63ef79b3dc5c1c1e486f905e483a4fcc62e6bda6bc3fe6affc50daad93
+size 4610

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 249.8, "n_evaluation_episodes": 10, "eval_datetime": "2023-07-31T14:36:04.499137"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 74.2, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-04T16:35:46.089962"}