Push agent to the Hub

README.md

@@ -0,0 +1,59 @@
+---
+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: -165.00 +/- 73.23
+      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
+'capture_video': False
+'num_envs': 32
+'num_steps': 128
+'anneal_lr': True
+'gae': True
+'gamma': 0.995
+'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': 'xianbin/ppo-LunarLander-v2-2'
+'batch_size': 4096
+'minibatch_size': 1024
+'env_id': 'LunarLander-v2'}
+  ```
+  

logs/events.out.tfevents.1690528905.cbe51853a075.10633.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21fe526f580f386cb9f924b2c3ada4b7fa76c5c0551e1983fa2ff5dbcf167916
+size 117100

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04aadae5d72f4b8e8ae191432277052c7a5fd17490c2999c7da6db07ea57897e
+size 42597

results.json

@@ -0,0 +1 @@
+{"env_id": "LunarLander-v2", "mean_reward": -164.99874724966392, "std_reward": 73.23170107242274, "n_evaluation_episodes": 10, "eval_datetime": "2023-07-28T07:22:19.502337"}