Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -12.38 +/- 63.66
+      value: 49.06 +/- 75.45
       name: mean_reward
       verified: false
 ---
@@ -40,7 +40,7 @@ model-index:
 'total_timesteps': 200000
 'learning_rate': 0.00025
 'num_envs': 4
-'num_steps': 256
+'num_steps': 128
 'anneal_lr': True
 'gae': True
 'gamma': 0.99
@@ -48,14 +48,14 @@ model-index:
 'num_minibatches': 4
 'update_epochs': 8
 'norm_adv': True
-'clip_coef': 0.15
+'clip_coef': 0.1
 'clip_vloss': True
 'ent_coef': 0.01
 'vf_coef': 0.5
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'jegeblad/ppo-Lunar'
-'batch_size': 1024
-'minibatch_size': 256}
+'batch_size': 512
+'minibatch_size': 128}
   ```
   

logs/events.out.tfevents.1748255405.65ffb41d1db7.40757.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02f151a6fc8baf79d334ec11373d7a84f437bacff59b9174bdd6ad3cc8f80078
+size 279827

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31a74a9c6e2193a542ccde9abbace685f9325f6007a3d283b20b77c71c44c07e
+oid sha256:fedd6a7e2e2ce2b30a8e31e67cd8da67e78831a4aee1fc4b9cc115819a3e21b1
 size 42898

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:798f1e132ded22ca990e0fd84492bf64497d0b9e80bf3f3c2ba30bddfe6fb9e4
-size 206758
+oid sha256:530f3aa04d63e8230a162226af855542acfb691abb7568b11da92f6a2d55c46b
+size 202242

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -12.37805635338265, "std_reward": 63.65869806712474, "n_evaluation_episodes": 10, "eval_datetime": "2025-05-26T10:28:16.703387"}
+{"env_id": "LunarLander-v2", "mean_reward": 49.064261782883186, "std_reward": 75.4465877577701, "n_evaluation_episodes": 10, "eval_datetime": "2025-05-26T10:37:31.736595"}