Push agent to the Hub

README.md

@@ -0,0 +1,49 @@
+---
+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: -26.75 +/- 72.19
+      name: mean_reward
+      verified: false
+---
+
+  # PPO Agent Playing LunarLander-v2
+
+  This is a trained model of a PPO agent playing LunarLander-v2.
+
+  # Hyperparameters
+  ```python
+  {'seed': 1
+'env_id': 'LunarLander-v2'
+'total_timesteps': 100000
+'num_envs': 8
+'num_steps': 128
+'gamma': 0.99
+'gae_lambda': 0.95
+'learning_rate': 0.0003
+'clip_range': 0.2
+'value_loss_coef': 0.5
+'entropy_loss_coef': 0.01
+'max_grad_norm': 0.5
+'update_epochs': 4
+'mini_batch_size': 64
+'eval_freq': 10
+'no_cuda': False
+'repo_id': 'jrauch/ppo-{env}'}
+  ```
+  

logs/events.out.tfevents.1681815849.JONAS-DESKTOP.22112.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f119bbb1ab17c940b804717a07dd177e6c1507f9ef5463182d7bf4ca97952df7
+size 51488

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e7ad1adebf9d49876d2a11ecf6538eb2d6faa3e08b8b3e089c0461f461d3dae
+size 42597

results.json

@@ -0,0 +1 @@
+{"env_id": "LunarLander-v2", "mean_reward": -26.751084709450634, "std_reward": 72.19191272619219, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-18T13:16:00.096105"}