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: -50.40 +/- 53.95
+      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'
+'gym_id': 'LunarLander-v2'
+'learning_rate': 0.00025
+'seed': 1
+'total_timesteps': 100000
+'torch_deterministic': True
+'cuda': True
+'track': False
+'wandb_project_name': 'ppo-implementation-details'
+'wandb_entity': None
+'capture_video': False
+'num_envs': 8
+'num_steps': 1024
+'anneal_lr': True
+'gae': True
+'gamma': 0.99
+'gae_lambda': 0.98
+'num_minibatches': 128
+'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
+'push_to_hf': False
+'repo_id': 'orepin/custom-ppo-LunarLander-v2-100k'
+'batch_size': 8192
+'minibatch_size': 64}
+  ```
+  

logs/events.out.tfevents.1685142190.Almiras-MacBook-Air.local.52036.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bebb3000562a5bea350d13ec2872dc8b7d3c51331ad5d71e919d46126822a2cc
+size 115002

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef9a0ddfbbe0c64fbacd6092c10682802cb912ca4d4c6b26eabf675292338aa7
+size 42469

results.json

@@ -0,0 +1 @@
+{"env_id": "LunarLander-v2", "mean_reward": -50.39595855855585, "std_reward": 53.95306064741359, "n_evaluation_episodes": 30, "eval_datetime": "2023-05-27T00:03:54.109587"}