Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -12.59 +/- 46.45
+      value: -155.26 +/- 78.99
       name: mean_reward
       verified: false
 ---
@@ -39,11 +39,11 @@ model-index:
 'env_id': 'LunarLander-v2'
 'total_timesteps': 1000000
 'learning_rate': 0.0001
-'num_envs': 4
+'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': 'ammr/ppo-LunarLander-v2'
-'batch_size': 4096
-'minibatch_size': 1024}
+'batch_size': 16384
+'minibatch_size': 4096}
   ```
   

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58ed15663e5229a47f68c44ac53604c002eb8ac4ab894d2b8905f6677e352af8
+oid sha256:50ff81186b18c1ff9fbd78bff6937f3f61bb370f8836cb021a39184810861989
 size 42469

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -12.586352569917254, "std_reward": 46.44567552178459, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-18T18:17:48.899658"}
+{"env_id": "LunarLander-v2", "mean_reward": -155.25774733359867, "std_reward": 78.99042596662213, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-18T18:24:12.797927"}