Upload . with huggingface_hub

README.md

@@ -16,12 +16,12 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: -2.55 +/- 0.50
+      value: 14.70 +/- 12.44
       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 5 of the Deep Reinforcement Learning Class: https://github.com/huggingface/deep-rl-class/tree/main/unit5
+  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
   

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 128, "n_training_episodes": 80000, "n_evaluation_episodes": 20, "max_t": 10000, "gamma": 0.999, "lr": 1e-05, "env_id": "Pixelcopter-PLE-v0", "state_space": 7, "action_space": 2}
+{"h_size": 64, "n_training_episodes": 15000, "n_evaluation_episodes": 10, "max_t": 15000, "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 sha256:8b82862c6259793dfd8d3e7eb591db569fb06ad342c5c54edeab86174a088781
-size 7263
+oid sha256:6fe730624adea5ff79bcc1dfa1f4aead7a0ac3e6d0e8e1e682e609c63b059b5b
+size 39239

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:143f8ac58d92935d60c2df26dca314361a7ad5bbd51ec81206c0a056590146a4
-size 3478
+oid sha256:ac58323082ca04c2313d147d38bb06efc27d29eccc32dfbbf2ec1ca3a71ce4bd
+size 9493

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": -2.55, "n_evaluation_episodes": 20, "eval_datetime": "2022-09-27T14:03:52.855644"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 14.7, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-13T04:23:34.625801"}