Upload folder using huggingface_hub

README.md

@@ -6,7 +6,7 @@ tags:
 - custom-implementation
 - deep-rl-class
 model-index:
-- name: Reinforce-Copter_V1
+- name: Reinforce-Copter_v1
   results:
   - task:
       type: reinforcement-learning
@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 13.10 +/- 14.00
+      value: 33.90 +/- 29.59
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 64, "n_training_episodes": 5000, "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": 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 sha256:6fd62fc16099b3a1f637e7266233fb746304907e7a35d34d3b7ea7c29105447e
+oid sha256:fa9faa5905f3e428955756ffa351728be667350fc8d1ca076ae41ee6a8d1cc2a
 size 39732

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 13.1, "n_evaluation_episodes": 10, "eval_datetime": "2025-03-31T08:19:13.579021"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 33.9, "n_evaluation_episodes": 10, "eval_datetime": "2025-03-31T15:18:25.148460"}