Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -92.23 +/- 103.93
+      value: 2.23 +/- 49.28
       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
+'gamma': 0.999
+'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': 'gstaff/ppo-LunarLander-v2'
-'batch_size': 512
-'minibatch_size': 128}
+'batch_size': 4096
+'minibatch_size': 1024}
   ```
   

logs/events.out.tfevents.1677450712.25f188cb86e1.18648.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02d63155afc94c7f438839d8e6f291ee2e9f96d71896fcca862c1877d5b72504
+size 998456

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebb378896b2cb4c43e971f50d7380e681cb99523b73cd341f85c99706c03d9df
+oid sha256:110aa72991bb5f3140765f311382aaaafa21488e163e20879b54c3c1fbf7e240
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -92.22848679221946, "std_reward": 103.92604005847194, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-26T22:26:00.177841"}
+{"env_id": "LunarLander-v2", "mean_reward": 2.232705035395269, "std_reward": 49.27606962965318, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-26T22:44:53.528912"}