Push agent to the Hub

README.md

@@ -0,0 +1,30 @@
+---
+tags:
+- LunarLander-v2
+- ppo
+- deep-reinforcement-learning
+- reinforcement-learning
+- custom-implementation
+- deep-rl-course
+model-index:
+- name: PPO
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: LunarLander-v2
+      type: LunarLander-v2
+    metrics:
+    - type: mean_reward
+      value: 110.87 +/- 52.96
+      name: mean_reward
+      verified: false
+---
+
+    # PPO Agent Playing LunarLander-v2
+
+    This is a trained model of a PPO agent playing LunarLander-v2.
+
+    # Hyperparameters
+    

logs/events.out.tfevents.1683335910.CAPTAIN-AMERICA.79570.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:329776b6e93ba83d57995a891495ffdd5da3fbe80a5459fcdb06034609bf8534
+size 787933

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88d4d087472dda6c14e18731ea083167c8c23f027ac3e0a36322be9b2b402a2d
+size 42597

results.json

@@ -0,0 +1 @@
+{"env_id": "LunarLander-v2", "mean_reward": 110.86753507108881, "std_reward": 52.963279937716614, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-05T21:39:59.342139"}