Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 77.38 +/- 66.24
+      value: 276.09 +/- 20.19
       name: mean_reward
       verified: false
 ---
@@ -32,7 +32,7 @@ model-index:
 'gym_id': 'LunarLander-v2'
 'learning_rate': 0.0003
 'seed': 1
-'total_timesteps': 1000000
+'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': 256
 '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': 1024
+'minibatch_size': 256}
   ```
   

logs/events.out.tfevents.1694629377.b693a32d7521.45896.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf6e6c67398b96505514ff04fe4c3defe973cba1091f6f21bfc8b02f580dfd4d
+size 4475525

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1eb62b37cb54ab4f5f9f1b3cfa2bf07f8feb30120bb1dae232b89b082e432cd2
+oid sha256:b3347ecae991e04763a6e029e1fb79738e161c97f733a1b0c7af0f6082dadce6
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 77.38195338611227, "std_reward": 66.23722862757693, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-13T18:14:18.483430"}
+{"env_id": "LunarLander-v2", "mean_reward": 276.08997855741995, "std_reward": 20.188224795713282, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-13T19:47:39.065764"}