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: -98.60 +/- 56.65
+      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.1711913294.J-Linux.45082.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab19d9837616210679b9bd83d7431209a114f74383281b0fd39bda32d1c7214a
+size 50409

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e824e9bfad1e5991784ff24348d593d61af8c211e1ffa5999ef6f4bfb8d71ac
+size 42898

results.json

@@ -0,0 +1 @@
+{"env_id": "LunarLander-v2", "mean_reward": -98.60308402179275, "std_reward": 56.652115910145056, "n_evaluation_episodes": 10, "eval_datetime": "2024-03-31T20:28:28.480263"}