Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 0.79 +/- 79.35
+      value: -74.81 +/- 75.57
       name: mean_reward
       verified: false
 ---
@@ -40,7 +40,7 @@ model-index:
 'total_timesteps': 50000
 'learning_rate': 0.0009
 'num_envs': 4
-'num_steps': 32
+'num_steps': 64
 'anneal_lr': True
 'gae': True
 'gamma': 0.999
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'Katelie/lunarlander-cleanrl-ppo'
-'batch_size': 128
-'minibatch_size': 32}
+'batch_size': 256
+'minibatch_size': 64}
   ```
   

logs/events.out.tfevents.1707494008.a74decb87bc7.7237.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4114d369578b80e52b6ae1f18b879b49c4f89748cbd61bb8f9045356d7e9945a
+size 150871

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f15075304a175f6a28bb5ebd660e4daf95c9f837f7984e84dbb166178cbdafdc
+oid sha256:1aaf599608c5b138a6c7fd95c163f0886f8a300a603cbddd5b2a041a7fae5f20
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 0.7926786516925972, "std_reward": 79.34957627542444, "n_evaluation_episodes": 10, "eval_datetime": "2024-02-09T15:52:17.870225"}
+{"env_id": "LunarLander-v2", "mean_reward": -74.81047080368151, "std_reward": 75.56735594655072, "n_evaluation_episodes": 10, "eval_datetime": "2024-02-09T15:54:22.811353"}