Upload folder using huggingface_hub

README.md

@@ -6,7 +6,7 @@ tags:
 - custom-implementation
 - deep-rl-class
 model-index:
-- name: Reinforce-pixelcopterv3
+- name: Reinforce-PixelCopterV3
   results:
   - task:
       type: reinforcement-learning
@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 35.90 +/- 30.95
+      value: 19.80 +/- 17.58
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 64, "n_training_episodes": 15000, "n_evaluation_episodes": 10, "max_t": 5000, "gamma": 0.98, "lr": 0.0002, "env_id": "Pixelcopter-PLE-v0", "state_space": 7, "action_space": 2}
+{"h_size": 64, "n_training_episodes": 30000, "n_evaluation_episodes": 10, "max_t": 5000, "gamma": 0.99, "lr": 0.00015, "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 sha256:38ef5a0053bef78e8da39d88dcf2ff868ba20c5e2aba86ab3a88296e512bc59d
+oid sha256:a8f6c1d0f66ccc1d5f5da474f1f2909c899d28c2ecde667ffa2eb4c2b64a2b04
 size 39732

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 35.9, "n_evaluation_episodes": 10, "eval_datetime": "2024-05-09T14:51:09.459614"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 19.8, "n_evaluation_episodes": 10, "eval_datetime": "2024-05-10T00:11:17.910014"}