Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -49.77 +/- 19.51
+      value: 89.18 +/- 74.58
       name: mean_reward
       verified: false
 ---
@@ -40,12 +40,12 @@ model-index:
 'total_timesteps': 1000000
 'learning_rate': 0.00025
 'num_envs': 16
-'num_steps': 128
+'num_steps': 1024
 'anneal_lr': True
 'gae': True
-'gamma': 0.99
-'gae_lambda': 0.95
-'num_minibatches': 4
+'gamma': 0.999
+'gae_lambda': 0.98
+'num_minibatches': 64
 'update_epochs': 4
 'norm_adv': True
 'clip_coef': 0.2
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'Ding-Qiang/ppo-LunarLander-v2-from-scratch'
-'batch_size': 2048
-'minibatch_size': 512}
+'batch_size': 16384
+'minibatch_size': 256}
   ```
   

logs/events.out.tfevents.1692534880.0fa77e911b8f.3573.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2bd6bb1492046195f21e3ade90f6c49edf756b15575d01badcec34a1723e0ef
+size 341729

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9b14eb65015a3d58c6311accf63829a2516ef8b480f8ca9d4582bf8e18d80b9
+oid sha256:1f72035783c405a905e04ad9b5fab05a508c6c4c25e7c7f2904f14c325373ac2
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -49.76632175469464, "std_reward": 19.514991340927573, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-20T11:31:42.246031"}
+{"env_id": "LunarLander-v2", "mean_reward": 89.17579997037024, "std_reward": 74.58199391297416, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-20T12:56:33.209586"}