Push agent to the Hub

README.md

@@ -1,6 +1,6 @@
 ---
 tags:
-- HumanoidBulletEnv-v0
+- AntBulletEnv-v0
 - ppo
 - deep-reinforcement-learning
 - reinforcement-learning
@@ -13,18 +13,18 @@ model-index:
       type: reinforcement-learning
       name: reinforcement-learning
     dataset:
-      name: HumanoidBulletEnv-v0
-      type: HumanoidBulletEnv-v0
+      name: AntBulletEnv-v0
+      type: AntBulletEnv-v0
     metrics:
     - type: mean_reward
-      value: 34.69 +/- 28.25
+      value: 455.82 +/- 18.68
       name: mean_reward
       verified: false
 ---
 
-  # PPO Agent Playing HumanoidBulletEnv-v0
+  # PPO Agent Playing AntBulletEnv-v0
 
-  This is a trained model of a PPO agent playing HumanoidBulletEnv-v0.
+  This is a trained model of a PPO agent playing AntBulletEnv-v0.
 
   # Hyperparameters
   ```python
@@ -36,7 +36,7 @@ model-index:
 'wandb_project_name': 'PPO-RL'
 'wandb_entity': None
 'capture_video': False
-'env_id': 'HumanoidBulletEnv-v0'
+'env_id': 'AntBulletEnv-v0'
 'total_timesteps': 2000000
 'learning_rate': 0.0003
 'num_envs': 4

logs/events.out.tfevents.1735044367.localhost.localdomain.16513.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82bc266bd57726d248f1c2a0d2f26f640a122b91aa6aee1d93d01f6decec4477
+size 374487

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a7ddc4e0736385b44d486224631063b865b619988facc71f16eadd33fa4ab2e
-size 65229
+oid sha256:0e241ade5a5c2e5e77aa021441ca983c580e78836d0b0578abf64d89365671ae
+size 54605

results.json

@@ -1 +1 @@
-{"env_id": "HumanoidBulletEnv-v0", "mean_reward": 34.694940668302586, "std_reward": 28.25282936524156, "n_evaluation_episodes": 30, "eval_datetime": "2024-12-24T05:39:04.934961"}
+{"env_id": "AntBulletEnv-v0", "mean_reward": 455.8249732242863, "std_reward": 18.679052794176723, "n_evaluation_episodes": 30, "eval_datetime": "2024-12-24T06:21:49.969169"}