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: -152.32 +/- 57.60
+      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.1704211346.bd2e885f77ef.10088.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8385f2462273b4450ffb6f1f5f6c52f5b6850c7b736642b95bacdca72e5a31ce
+size 110610

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eebf5a5a16875be995710855a60858096d38ae9c5b46bdd5cdb1222c3c6b26d9
+size 42898

results.json

@@ -0,0 +1 @@
+{"env_id": "LunarLander-v2", "mean_reward": -152.31851882070026, "std_reward": 57.59679655030862, "n_evaluation_episodes": 10, "eval_datetime": "2024-01-02T16:02:51.115193"}