Push agent to the Hub

README.md

@@ -0,0 +1,60 @@
+---
+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: 158.41 +/- 16.08
+      name: mean_reward
+      verified: false
+---
+
+  # PPO Agent Playing LunarLander-v2
+
+  This is a trained model of a PPO agent playing LunarLander-v2.
+
+  # Hyperparameters
+  ```python
+  {'exp_name': 'main'
+'seed': 1
+'torch_deterministic': True
+'cuda': True
+'track': True
+'wandb_project_name': 'cleanRL'
+'wandb_entity': None
+'capture_video': False
+'env_id': 'LunarLander-v2'
+'total_timesteps': 10000000
+'learning_rate': 0.0005
+'num_envs': 32
+'num_steps': 256
+'anneal_lr': True
+'gamma': 0.99
+'gae_lambda': 0.98
+'num_minibatches': 4
+'update_epochs': 8
+'norm_adv': True
+'clip_coef': 0.2
+'clip_vloss': True
+'ent_coef': 0.01
+'vf_coef': 0.5
+'max_grad_norm': 0.5
+'target_kl': None
+'repo_id': 'LOGQS/ppo-LunarLander-v2'
+'batch_size': 8192
+'minibatch_size': 2048}
+  ```
+  

logs/events.out.tfevents.1687540255.LOGOS.17292.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c627e03394feb2a6ca74c76a01535dc9af12fe1b18b6f50a20f798364b8e2df7
+size 2579200

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6aa29c960da102799923a73c78b55f8a597fa3c254fff838b959974b0df283e
+size 42469

results.json

@@ -0,0 +1 @@
+{"env_id": "LunarLander-v2", "mean_reward": 158.40815273087497, "std_reward": 16.079035657973428, "n_evaluation_episodes": 10, "eval_datetime": "2023-06-23T21:22:48.465567"}