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: -145.50 +/- 15.20
+      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.1683119562.vova.519074.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ea3225808d6c4fdc7f55e478c926cf330dd235dae8f102dec91ad159b7d7f63
+size 44903

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb51ab5ac25fddee4b88f6c9bc6ce5a5e4f775ac586a6f1a7918893c0195d44b
+size 42817

results.json

@@ -0,0 +1 @@
+{"env_id": "LunarLander-v2", "mean_reward": -145.4988908133269, "std_reward": 15.199408397025728, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-03T23:13:55.611249"}