Upload folder using huggingface_hub

README.md

@@ -6,7 +6,7 @@ tags:
 - custom-implementation
 - deep-rl-class
 model-index:
-- name: Reinforce-pixelcopter
+- name: Reinforce-pixelCopter
   results:
   - task:
       type: reinforcement-learning
@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 7.90 +/- 4.66
+      value: 13.93 +/- 14.27
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 64, "n_training_episodes": 10000, "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": 5000, "n_evaluation_episodes": 100, "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:bc65288cfffe0f26f7d1af9d66891237a4453f6e144a3df72df6948cb12bf308
-size 38983
+oid sha256:89a48d623d63554863e11a93b7d6364e12ce96717137efd41ff5b6a72b8f962d
+size 39239

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 7.9, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-22T23:25:12.123981"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 13.93, "n_evaluation_episodes": 100, "eval_datetime": "2023-05-17T23:18:59.374213"}