Upload folder using huggingface_hub

README.md

@@ -1,10 +1,10 @@
 ---
 tags:
 - Pixelcopter-PLE-v0
-- reinforce
+- dqn
+- deep-q-learning
 - reinforcement-learning
 - custom-implementation
-- deep-rl-class
 model-index:
 - name: Reinforce-Pixelcopter-PLE-v0
   results:
@@ -16,12 +16,10 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 23.00 +/- 19.31
+      value: 1.00 +/- 5.71
       name: mean_reward
       verified: false
 ---
 
-  # **Reinforce** Agent playing **Pixelcopter-PLE-v0**
-  This is a trained model of a **Reinforce** agent playing **Pixelcopter-PLE-v0** .
-  To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
-  
+# **DQN** Agent playing **Pixelcopter-PLE-v0**
+This is a trained model of a **Deep Q-Network (DQN)** agent playing **Pixelcopter-PLE-v0**.

dqn_model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0f8a949b840140b868572b8a7ddb5ea92a69aa3a465846f147ac608dc5909cd
+size 40152

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 256, "n_training_episodes": 4000, "n_evaluation_episodes": 10, "max_t": 20000, "gamma": 0.99, "lr": 0.0001, "clip_eps": 0.2, "entropy_beta": 0.05, "K_epochs": 4, "env_id": "Pixelcopter-PLE-v0", "state_space": 7, "action_space": 2}
+{"h_size": 64, "gamma": 0.99, "lr": 0.0001, "batch_size": 64, "buffer_size": 50000, "epsilon_start": 1.0, "epsilon_end": 0.01, "epsilon_decay": 10000, "target_update": 1000, "n_episodes": 2500, "max_t": 500, "n_evaluation_episodes": 10, "env_id": "Pixelcopter-PLE-v0"}

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 23.0, "n_evaluation_episodes": 10, "eval_datetime": "2025-02-14T06:15:44.399292"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 1.0, "n_evaluation_episodes": 10, "eval_datetime": "2025-02-17T00:35:50.531542"}