Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -127.23 +/- 113.87
+      value: 79.36 +/- 96.14
       name: mean_reward
       verified: false
 ---
@@ -34,16 +34,16 @@ model-index:
 'cuda': True
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 50000
+'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
+'update_epochs': 20
 'norm_adv': True
 'clip_coef': 0.2
 'clip_vloss': True
@@ -52,7 +52,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'chavicoski/PPO-CleanRL-LunarLander-v2'
-'batch_size': 512
-'minibatch_size': 128}
+'batch_size': 4096
+'minibatch_size': 1024}
   ```
   

logs/events.out.tfevents.1676822873.4244a7e9a1ff.1.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d580bec0aac40ed833c5392fc6fdb2de50ae7ae1040546791f6b809578c8276d
+size 348152

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed45dd80528a6e3ca19666dd27ca331589efa7153194dd867c91834478a24d6f
+oid sha256:1eb813922f2ad1115521373f023c81a73b9e3b6a0345600a5b226b4293e68204
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -127.23007399415556, "std_reward": 113.87273027917782, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-19T16:03:52.112372"}
+{"env_id": "LunarLander-v2", "mean_reward": 79.36196285043475, "std_reward": 96.13923650939194, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-19T16:21:03.451435"}