Push agent to the Hub

README.md

@@ -0,0 +1,61 @@
+---
+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: -88.37 +/- 36.25
+      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': 'ppo'
+'seed': 1
+'torch_deterministic': True
+'cuda': True
+'track': False
+'wandb_project_name': 'cleanRL'
+'wandb_entity': None
+'capture_video': False
+'env_id': 'LunarLander-v2'
+'total_timesteps': 100000
+'learning_rate': 0.00025
+'num_envs': 16
+'num_steps': 1024
+'anneal_lr': True
+'gae': True
+'gamma': 0.999
+'gae_lambda': 0.98
+'num_minibatches': 256
+'update_epochs': 4
+'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': 'kalmi901/ppo-CleanRL-LunarLander-v2'
+'batch_size': 16384
+'minibatch_size': 64}
+  ```
+  

logs/events.out.tfevents.1727002407.fa36c63a5d52.13700.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4f9b991f169f4b6cc4a07cc041c5ebc5290a90a5eddf84ee30fa8169958b5e2
+size 118734

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0b1588a87247e02f5eef0468109f0e1a4fb7190be6d3c6c69f6eef8e2199912
+size 147730

results.json

@@ -0,0 +1 @@
+{"env_id": "LunarLander-v2", "mean_reward": -88.3738041112943, "std_reward": 36.24991057245153, "n_evaluation_episodes": 10, "eval_datetime": "2024-09-22T10:54:33.984058"}