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: -184.96 +/- 109.39
+      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.1695053400.rhmmedcatt-ProLiant-ML350-Gen10.117870.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8d2db57017d0edcbaad28c6737775fecebe4b775be9898ed8259cfb287b4974
+size 122697

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffcfdba305543de60331a5d534e90bddecbee681b86f4c0a1dbf2d44568528c2
+size 42597

results.json

@@ -0,0 +1 @@
+{"env_id": "LunarLander-v2", "mean_reward": -184.95764915464142, "std_reward": 109.39092528107228, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-18T17:10:35.704811"}