Push agent to the Hub

README.md

@@ -0,0 +1,40 @@
+---
+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: -101.69 +/- 95.52
+      name: mean_reward
+      verified: false
+---
+
+  # PPO Agent Playing LunarLander-v2
+
+  This is a trained model of a PPO agent playing LunarLander-v2.
+    
+  # Hyperparameters
+  ```python
+  {'max_frames': 400000
+'gamma': 0.95
+'PPO_epsilon': 0.2
+'max_t': 99
+'target_nets_update_freq': 50
+'lr': 0.00025
+'entropy_coef': 0.01
+'env_id': 'LunarLander-v2'}
+  ```
+  

logs/events.out.tfevents.1685131121.f0828af4afe6.1228.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33de27691f684efdfbf546df0102a7100f2552ae365cf7d2f2484e763e360451
+size 88

logs/events.out.tfevents.1685131323.f0828af4afe6.1228.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c21bf1e7bbdaa43e8247e8aec57e098a797cc38dafd081c14c3da4a20272c7cc
+size 125631

logs/events.out.tfevents.1685132511.f0828af4afe6.1228.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d57354d88ff90a5c5e383bb68a18fa6b92c236373575873160749dc09f6d0821
+size 134009

logs/events.out.tfevents.1685132954.f0828af4afe6.1228.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bdcdcf4a03df2dd7da6cf3d1b8c2924d27e06d035878cb1583c898eb4a04cc8
+size 240268

logs/events.out.tfevents.1685134337.f0828af4afe6.1228.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05bac3483d65f8da16eb96c1fa8df1177c5f5b90c8cb0adb3bb2693f7f6c9c3a
+size 259797

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32fa5b2589a720db0651c25328263740e2e51b10622a2b696f0c274f88686123
+size 5319

results.json

@@ -0,0 +1 @@
+{"env_id": "LunarLander-v2", "mean_reward": -101.68873075582687, "std_reward": 95.51958858948541, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-26T21:21:36.222293"}