Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -166.10 +/- 82.15
+      value: 117.28 +/- 46.77
       name: mean_reward
       verified: false
 ---
@@ -32,16 +32,16 @@ model-index:
 'gym_id': 'LunarLander-v2'
 'learning_rate': 0.00025
 'seed': 1
-'total_timesteps': 100000
+'total_timesteps': 5000000
 'torch_deterministic': True
 'cuda': True
 'capture_video': False
 'num_envs': 4
-'num_steps': 128
+'num_steps': 1024
 'anneal_lr': True
 'gae': True
-'gamma': 0.99
-'gae_lambda': 0.95
+'gamma': 0.999
+'gae_lambda': 0.98
 'num_minibatches': 4
 'update_epochs': 4
 'norm_adv': True
@@ -52,7 +52,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'thackerhelik/ppo-CleanRL-LunarLander-v2'
-'batch_size': 512
-'minibatch_size': 128}
+'batch_size': 4096
+'minibatch_size': 1024}
   ```
   

logs/events.out.tfevents.1686763665.f20884bd5bb1.12826.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06ab458747a2357ef7f724ab0ba630a047acc269d38731fc20b4f32d425c076c
+size 1871094

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b59e0b234a7f4b54554eef94c644ff9362eafceb744d93ebb6bc7256b18a2095
+oid sha256:3f4ab747df617895ad7078591e207ab888c81939e7533570858e5ceb4ecdfabb
 size 42597

results.json

@@ -1 +1 @@
-{"gym_id": "LunarLander-v2", "mean_reward": -166.10243966556968, "std_reward": 82.14755964344688, "n_evaluation_episodes": 10, "eval_datetime": "2023-06-14T17:21:24.818420"}
+{"gym_id": "LunarLander-v2", "mean_reward": 117.27845939363245, "std_reward": 46.76986282139113, "n_evaluation_episodes": 10, "eval_datetime": "2023-06-14T19:39:55.047355"}