Push agent to the Hub

README.md

@@ -1,6 +1,6 @@
 ---
 tags:
-- CartPole-v1
+- LunarLander-v2
 - ppo
 - deep-reinforcement-learning
 - reinforcement-learning
@@ -13,18 +13,18 @@ model-index:
       type: reinforcement-learning
       name: reinforcement-learning
     dataset:
-      name: CartPole-v1
-      type: CartPole-v1
+      name: LunarLander-v2
+      type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 64.60 +/- 27.55
+      value: -132.77 +/- 74.31
       name: mean_reward
       verified: false
 ---
 
-  # PPO Agent Playing CartPole-v1
+  # PPO Agent Playing LunarLander-v2
 
-  This is a trained model of a PPO agent playing CartPole-v1.
+  This is a trained model of a PPO agent playing LunarLander-v2.
     
   # Hyperparameters
   ```python
@@ -36,7 +36,7 @@ model-index:
 'wandb_project_name': 'cleanRL'
 'wandb_entity': None
 'capture_video': False
-'env_id': 'CartPole-v1'
+'env_id': 'LunarLander-v2'
 'total_timesteps': 100000
 'learning_rate': 0.00025
 'num_envs': 4
@@ -44,7 +44,7 @@ model-index:
 'anneal_lr': True
 'gae': True
 'gamma': 0.999
-'gae_lambda': 0.99
+'gae_lambda': 0.95
 'num_minibatches': 4
 'update_epochs': 4
 'norm_adv': True

logs/events.out.tfevents.1683009273.fabio-Katana-GF66-12UC.10693.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cd228db4493199a82d9c70fe32d9736efda5fce7a9a4800f653c1066c53b1bc
+size 136974

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8abf9208b60a055fa6087b91d44acf023e07d7ecc71a85604c96e0a6c556fe60
-size 39909
+oid sha256:3499e5fcb28388a3097aa7386878c5784b2004bc7485f9e6b22629429b616520
+size 42469

results.json

@@ -1 +1 @@
-{"env_id": "CartPole-v1", "mean_reward": 64.6, "std_reward": 27.547050658827345, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-02T08:32:05.578145"}
+{"env_id": "LunarLander-v2", "mean_reward": -132.77144667518687, "std_reward": 74.30547591376975, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-02T08:37:56.321547"}