Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 141.05 +/- 46.39
+      value: 128.38 +/- 47.93
       name: mean_reward
       verified: false
 ---
@@ -32,7 +32,7 @@ model-index:
 'gym_id': 'LunarLander-v2'
 'learning_rate': 0.0003
 'seed': 1
-'total_timesteps': 2000000
+'total_timesteps': 5000000
 'torch_deterministic': True
 'cuda': True
 'track': False
@@ -41,7 +41,7 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'num_envs': 4
-'num_steps': 512
+'num_steps': 2048
 'anneal_lr': True
 'gae': True
 'gamma': 0.999
@@ -56,7 +56,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'FredericProtat/ppo-LunarLander-v2'
-'batch_size': 2048
-'minibatch_size': 512}
+'batch_size': 8192
+'minibatch_size': 2048}
   ```
   

logs/events.out.tfevents.1695040791.a84421aea25b.1664.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd591ecdcaf87d85a76e5c572e66296cc561a934400c08438b04c3a9243add1a
+size 1488873

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7e2c87b2fd27cc5b95c5c9b41b738d55c3977024ed2db5e95d78f7f714aea13
+oid sha256:8528e4ad0d00222dbcab0c8d2703ed8ddf0f5a4175cc59bbfc662a671d74fcdb
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 141.05474180844732, "std_reward": 46.39020319826474, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-16T18:05:32.980075"}
+{"env_id": "LunarLander-v2", "mean_reward": 128.38294366084426, "std_reward": 47.92548230425013, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-18T14:43:20.641219"}