Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -17.67 +/- 117.76
+      value: 58.18 +/- 80.80
       name: mean_reward
       verified: false
 ---
@@ -40,11 +40,11 @@ model-index:
 'total_timesteps': 1000000
 'learning_rate': 0.00025
 'num_envs': 4
-'num_steps': 128
+'num_steps': 1024
 'anneal_lr': True
 'gae': True
 'gamma': 0.99
-'gae_lambda': 0.95
+'gae_lambda': 0.98
 'num_minibatches': 4
 'update_epochs': 4
 'norm_adv': True
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'bonadio/LunarLander-PPO-unit8'
-'batch_size': 512
-'minibatch_size': 128}
+'batch_size': 4096
+'minibatch_size': 1024}
   ```
   

logs/events.out.tfevents.1676571104.a72fabec5a78.15289.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d83c97eea14d51d5f4b601cb6358c4125e82b9582b768e5e48f6a058e45a8b6
+size 654106

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab15a16b18b87bf962ef37e699d27733152d033658070d279c74e1eede715b34
+oid sha256:d838be9399a654c95f4083ae89eef0d4097ad6f34b563ede47e11994a3649a69
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -17.671538775258963, "std_reward": 117.76015621919962, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-16T18:04:41.889779"}
+{"env_id": "LunarLander-v2", "mean_reward": 58.1785201697326, "std_reward": 80.7997654572084, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-16T18:34:11.248232"}