Push agent to the Hub

README.md

@@ -0,0 +1,62 @@
+---
+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: -177.92 +/- 89.11
+      name: mean_reward
+      verified: false
+---
+
+  # PPO Agent Playing LunarLander-v2
+
+  This is a trained model of a PPO agent playing LunarLander-v2.
+    
+  # Hyperparameters
+  ```python
+  {'fff': '/root/.local/share/jupyter/runtime/kernel-d3563d3a-fcb2-4f06-b5c4-b7d025c7a55d.json'
+'exp_name': 'tempname'
+'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': 4
+'num_steps': 256
+'anneal_lr': True
+'gae': True
+'gamma': 0.99
+'gae_lambda': 0.95
+'num_minibatches': 4
+'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': 'kaljr/ppo-cleanRL-LunarLander-v2'
+'batch_size': 1024
+'minibatch_size': 256}
+  ```
+  

logs/events.out.tfevents.1708999580.22f33481509a.455.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43ce1d9c68faa7c800bef1a0556039668879359fefd587ebfb473306eb9fea11
+size 171833

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d1f079b9a9f92f2ea01e18643d4e531d466c28666b249c2998920a6c2456545
+size 42898

results.json

@@ -0,0 +1 @@
+{"env_id": "LunarLander-v2", "mean_reward": -177.92438497450198, "std_reward": 89.11115906382888, "n_evaluation_episodes": 10, "eval_datetime": "2024-02-27T02:07:18.935477"}