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: -51.91 +/- 38.82
+      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.1677850593.tensorbook.71636.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4779c34f2a0ca2234d360d763d0d76d6fb49e3338f222706e2e9ebc1e2c34371
+size 206278

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33a1e9044374702f9ca54180674594738a9e7e4ac71bd1f958e14c7de8c61251
+size 42817

results.json

@@ -0,0 +1 @@
+{"env_id": "LunarLander-v2", "mean_reward": -51.91132276331892, "std_reward": 38.82108719915925, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-03T14:37:21.128492"}