Push agent to the Hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+replay.mp4 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,6 +1,6 @@
 ---
 tags:
-- CartPole-v1
+- HalfCheetahBulletEnv-v0
 - 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: HalfCheetahBulletEnv-v0
+      type: HalfCheetahBulletEnv-v0
     metrics:
     - type: mean_reward
-      value: 191.10 +/- 70.41
+      value: -1605.41 +/- 93.38
       name: mean_reward
       verified: false
 ---
 
-  # PPO Agent Playing CartPole-v1
+  # PPO Agent Playing HalfCheetahBulletEnv-v0
 
-  This is a trained model of a PPO agent playing CartPole-v1.
+  This is a trained model of a PPO agent playing HalfCheetahBulletEnv-v0.
 
   # Hyperparameters
   ```python
@@ -32,30 +32,30 @@ model-index:
 'seed': 1
 'torch_deterministic': True
 'cuda': True
-'track': False
-'wandb_project_name': 'cleanRL-PPO'
+'track': True
+'wandb_project_name': 'PPO-RL'
 'wandb_entity': None
 'capture_video': False
-'env_id': 'CartPole-v1'
-'total_timesteps': 50000
-'learning_rate': 0.00025
-'num_envs': 4
-'num_steps': 128
+'env_id': 'HalfCheetahBulletEnv-v0'
+'total_timesteps': 2000
+'learning_rate': 0.0003
+'num_envs': 1
+'num_steps': 2048
 'anneal_lr': True
 'gae': True
 'gamma': 0.99
 'gae_lambda': 0.95
-'num_minibatches': 4
-'update_epochs': 4
+'num_minibatches': 32
+'update_epochs': 10
 'norm_adv': True
 'clip_coef': 0.2
 'clip_vloss': True
-'ent_coef': 0.01
+'ent_coef': 0.0
 'vf_coef': 0.5
 'max_grad_norm': 0.5
 'target_kl': 0.02
 'repo_id': 'kismet163/ppo-LunarLander-v2'
-'batch_size': 512
-'minibatch_size': 128}
+'batch_size': 2048
+'minibatch_size': 64}
   ```
   

logs/events.out.tfevents.1735013103.yoshii.693.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a9475387a1f10ad7b8cb4b1c008de9cb3c2d4fd75c762bdd797754fd0a59110
+size 746

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c3faacfb5d84e64cd22a826585cee7f78968ce7d3501f6841958d6deb6580cd
-size 40466
+oid sha256:d576ef1926481073887eb62cba4c0011a7bd1181cac1b5dbd3c4667b2377db0f
+size 52941

results.json

@@ -1 +1 @@
-{"env_id": "CartPole-v1", "mean_reward": 191.1, "std_reward": 70.41086563876345, "n_evaluation_episodes": 30, "eval_datetime": "2024-12-23T02:09:26.124704"}
+{"env_id": "HalfCheetahBulletEnv-v0", "mean_reward": -1605.4089231533642, "std_reward": 93.37885720626618, "n_evaluation_episodes": 30, "eval_datetime": "2024-12-23T21:06:09.713043"}