Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -173.93 +/- 80.63
+      value: 14.68 +/- 65.14
       name: mean_reward
       verified: false
 ---
@@ -30,9 +30,9 @@ model-index:
   ```python
   {'exp_name': 'ppo'
 'gym_id': 'LunarLander-v2'
-'learning_rate': 0.00025
+'learning_rate': 0.0003
 'seed': 1
-'total_timesteps': 50000
+'total_timesteps': 500000
 'torch_deterministic': True
 'cuda': True
 'capture_video': False
@@ -40,14 +40,14 @@ model-index:
 'wandb_project_name': 'cleanRL'
 'wandb_entity': None
 'repo_id': 'DarkRodry/unit8_LunarLander-v2'
-'num_envs': 4
-'num_steps': 128
+'num_envs': 8
+'num_steps': 2048
 'anneal_lr': True
 'gae': True
 'gamma': 0.99
-'gae_lambda': 0.95
+'gae_lambda': 0.96
 'num_minibatches': 4
-'update_epochs': 4
+'update_epochs': 10
 'norm_adv': True
 'clip_coef': 0.2
 'clip_vloss': True
@@ -55,7 +55,7 @@ model-index:
 'vf_coef': 0.5
 'max_grad_norm': 0.5
 'target_kl': None
-'batch_size': 512
-'minibatch_size': 128}
+'batch_size': 16384
+'minibatch_size': 4096}
   ```
   

logs/events.out.tfevents.1696330333.c3a73f0993b6.2925.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aec1a433be8b8be1d94410acc6b97c981f7cd56ec2082d9f3829fd61aa3e5d12
+size 305535

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c706c81696f37ceaeb74d41e1262ec54c4e2f63b8cbb791c8b01decf796f6a53
+oid sha256:4cd52a55e51e89e31f7537dfe34a1260c9d7017fa8149c4c1422059ea1356cb6
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -173.92783436736062, "std_reward": 80.63378637535602, "n_evaluation_episodes": 10, "eval_datetime": "2023-10-02T12:35:08.485841"}
+{"env_id": "LunarLander-v2", "mean_reward": 14.684392486455948, "std_reward": 65.14121646298042, "n_evaluation_episodes": 10, "eval_datetime": "2023-10-03T10:58:51.729677"}