Push Reinforce agent to the Hub

.gitattributes

@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zstandard 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 +1,25 @@
+---
+tags:
+- Pong-PLE-v0
+- reinforce
+- reinforcement-learning
+- custom-implementation
+- deep-rl-class
+model-index:
+- name: Reinforce-Pong
+  results:
+  - metrics:
+    - type: mean_reward
+      value: -16.00 +/- 0.00
+      name: mean_reward
+    task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: Pong-PLE-v0
+      type: Pong-PLE-v0
+---
+
+  # **Reinforce** Agent playing **Pong-PLE-v0**
+  This is a trained model of a **Reinforce** agent playing **Pong-PLE-v0** .
+  

hyperparameters.json

@@ -0,0 +1 @@
+{"h_size": 64, "n_training_episodes": 10000, "n_evaluation_episodes": 10, "max_t": 5000, "gamma": 0.99, "lr": 0.01, "env_id": "Pong-PLE-v0", "state_space": 7, "action_space": 3}

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:502a10e5ecc485979e7c05be382b88562c92bf7a7705307177a41b1b1ef71af3
+size 39447

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed0c04319cf92131228bb3493c5b9dc253f2c283841699d2e56f3f28b5fcf19a
+size 14816

results.json

@@ -0,0 +1 @@
+{"env_id": "Pong-PLE-v0", "mean_reward": -16.0, "n_evaluation_episodes": 10, "eval_datetime": "2022-07-03T16:28:36.363353"}