Upload . with huggingface_hub

README.md

@@ -16,12 +16,12 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 11.10 +/- 9.15
+      value: 18.90 +/- 8.83
       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": 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}
+{"h_size": 64, "n_training_episodes": 36000, "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 sha256:746dc7bd3a14d7d42e5de8ce7d024482189cddb8bc3f6522765e34b0755e70ee
-size 4703
+oid sha256:23a2bd95b3f6d4c23afcec63484d8f211a38d3f06cc66226dd20f73dc235a4e2
+size 38983

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ccdf130dd90569542f5260ea87053994caa1e5c3017efacfca63d41c628ab2a
-size 21848
+oid sha256:f2c95b5d295d8cc154822045a1e4ecea59c1387f6524f77e582b1fc107c51312
+size 8612

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 11.1, "n_evaluation_episodes": 10, "eval_datetime": "2022-11-10T10:24:17.013845"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 18.9, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-31T19:58:01.449925"}