Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -115.35 +/- 38.73
+      value: -178.58 +/- 110.74
       name: mean_reward
       verified: false
 ---
@@ -29,7 +29,7 @@ model-index:
   # Hyperparameters
   ```python
   {'exp_name': 'unit8'
-'seed': 1
+'seed': 24
 'torch_deterministic': True
 'cuda': True
 'track': False
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 70000
+'total_timesteps': 100000
 'learning_rate': 1e-05
 'num_envs': 4
 'num_steps': 1024

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a89ccbc2e7429d05d6e639d20ce746e56d997be51048bd1c047ad4c9579f0df
+oid sha256:3525dd5ddab208f44bdccd23598d544ffcabcde26c52baee8347ca97a4076fd4
 size 42469

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -115.34768303981346, "std_reward": 38.73395087840405, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-18T18:04:45.654418"}
+{"env_id": "LunarLander-v2", "mean_reward": -178.57653564432158, "std_reward": 110.73598896001421, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-18T18:06:15.971990"}