Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -186.54 +/- 103.35
+      value: -198.21 +/- 108.14
       name: mean_reward
       verified: false
 ---
@@ -39,11 +39,11 @@ model-index:
 'env_id': 'LunarLander-v2'
 'total_timesteps': 50000
 'learning_rate': 0.00025
-'num_envs': 4
-'num_steps': 128
+'num_envs': 16
+'num_steps': 1024
 'anneal_lr': True
 'gae': True
-'gamma': 0.99
+'gamma': 0.999
 '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': 'andyleow/PPO-LunarLander-v2'
-'batch_size': 512
-'minibatch_size': 128}
+'batch_size': 16384
+'minibatch_size': 4096}
   ```
   

logs/events.out.tfevents.1684283955.6581931b20e0.27931.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6916cee242246fd01149eb03881ea9bd2f8a34d04723f241d6c5283e523c19e
+size 60494

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdcf78178ab033a93b34f7326d70cc42208f7483f1f35803a03aad5050e0f842
+oid sha256:321ed78e883eac613a1e1bfbba5a728d3df49f45aa6e0182d7d7bd3c74e49f44
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -186.54397901749007, "std_reward": 103.35288167084695, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-17T00:27:48.791266"}
+{"env_id": "LunarLander-v2", "mean_reward": -198.20880636186467, "std_reward": 108.13639909684457, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-17T00:39:39.134376"}