Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -134.94 +/- 69.69
+      value: -17.36 +/- 61.14
       name: mean_reward
       verified: false
 ---
@@ -38,12 +38,12 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 50000
-'learning_rate': 0.00025
+'learning_rate': 0.001
 'num_envs': 4
-'num_steps': 128
+'num_steps': 512
 'anneal_lr': True
 'gae': True
-'gamma': 1.02
+'gamma': 0.99
 'gae_lambda': 0.95
 'num_minibatches': 4
 'update_epochs': 4
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'soonchang/ppo-CartPole-v1'
-'batch_size': 512
-'minibatch_size': 128}
+'batch_size': 2048
+'minibatch_size': 512}
   ```
   

logs/events.out.tfevents.1703596722.cybertron.1943.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:194a40c64207014f77b9cc6619c9f4975639b1a4cdd711a2128c9b9cb19dde43
+size 42719

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e868488144d8cf2fec4ab7315faf748edc5f266f057701efadd92536376a98bc
+oid sha256:4b6812619c4ca5b633d049f2080cfc64baa4325f25c9b5111372fff4ac2eb15b
 size 672534

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -134.93791757388504, "std_reward": 69.68858360606443, "n_evaluation_episodes": 10, "eval_datetime": "2023-12-26T21:17:26.452827"}
+{"env_id": "LunarLander-v2", "mean_reward": -17.35806012785114, "std_reward": 61.14206688118449, "n_evaluation_episodes": 10, "eval_datetime": "2023-12-26T21:19:42.690550"}