Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -29.43 +/- 80.82
+      value: -46.19 +/- 61.46
       name: mean_reward
       verified: false
 ---
@@ -38,12 +38,12 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 500000
-'learning_rate': 0.0003
+'learning_rate': 0.0001
 'num_envs': 4
-'num_steps': 128
+'num_steps': 256
 'anneal_lr': True
 'gae': True
-'gamma': 0.99
+'gamma': 0.997
 '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': 'yangzhou301/ppo-LunarLander-v2-unit8'
-'batch_size': 512
-'minibatch_size': 128}
+'batch_size': 1024
+'minibatch_size': 256}
   ```
   

logs/events.out.tfevents.1705115148.832745b025f2.28459.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f32612936d1a50f22e8414b12022144b3f458b4c47406081e24d1b9e135373e2
+size 599411

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c09c485542610dab203eed0e92d69924acd0493d3cb58641864ba5fe7bdae384
+oid sha256:601ca494bbf278aaa25fbbb6d1e8e8fd52fae5260987482d43ac22e75d9f898a
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -29.42555583684875, "std_reward": 80.82014026922005, "n_evaluation_episodes": 10, "eval_datetime": "2024-01-13T02:41:09.020991"}
+{"env_id": "LunarLander-v2", "mean_reward": -46.18960771287406, "std_reward": 61.457825887849964, "n_evaluation_episodes": 10, "eval_datetime": "2024-01-13T03:14:03.930331"}