Push Reinforce agent to the Hub

.gitattributes

@@ -30,3 +30,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.mp4 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,27 @@
+---
+tags:
+- Pixelcopter-PLE-v0
+- reinforce
+- reinforcement-learning
+- custom-implementation
+- deep-rl-class
+model-index:
+- name: Reinforce-Pixelcopter-PLE-v0
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: Pixelcopter-PLE-v0
+      type: Pixelcopter-PLE-v0
+    metrics:
+    - type: mean_reward
+      value: -0.20 +/- 1.83
+      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
+  

hyperparameters.json

@@ -0,0 +1 @@
+{"h_size": 64, "n_training_episodes": 1000, "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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6413836d62a9ba4560d4957b1e29412d8256e95cabbc7ad4e83c4c7e8c379c33
+size 4703

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8c572e934fa2556a532f19661551ff3e3445065f52479fb3bc3ddfec9eca7dc
+size 5578

results.json

@@ -0,0 +1 @@
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": -0.2, "n_evaluation_episodes": 10, "eval_datetime": "2022-10-02T05:42:41.211454"}