Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -22.37 +/- 86.74
+      value: -144.72 +/- 68.78
       name: mean_reward
       verified: false
 ---
@@ -40,11 +40,11 @@ model-index:
 'total_timesteps': 1000000
 'learning_rate': 0.0001
 'num_envs': 16
-'num_steps': 256
+'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': 'Schwarzschild009/hm-ppo-LunarLander-v2'
-'batch_size': 4096
-'minibatch_size': 1024}
+'batch_size': 16384
+'minibatch_size': 4096}
   ```
   

logs/events.out.tfevents.1683350279.5c24354cda09.3905.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3aa5a6020d0c9ec7d8a34c0e74d76ff8e86a08e7e4cc0299e94c047f15579085
+size 1238739

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63a76a9ebe075e15003a906568d175698752a662e6e98066c1c27b679d3c92e8
+oid sha256:b73ab162615b132d85334829fb7a582d41d964446b65ecb52fed62b02e45ab32
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -22.369779199748347, "std_reward": 86.7358430017376, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-05T23:14:16.645458"}
+{"env_id": "LunarLander-v2", "mean_reward": -144.72291871053557, "std_reward": 68.77537290848531, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-06T05:23:41.400249"}