policy is rad

src/main.rs

@@ -1,18 +1,22 @@
 mod policy;
+mod pingEsp32;
+
 use anyhow::{Context, Result};
-// fn main() -> Result<()> {
-//     //循环
-//     for _ in 0..10 {
-//         let action = policy::policy([0.0; 36])?;
-//         println!("模型输出: {action:?}");
-//     }
-//     Ok(())
-// }
+fn main() -> Result<()> {
+    //while循环
+    let mut i = 0;
+    while i < 10 {
+        let action = policy::policy([i as f32 *0.05; 36])?;
+        println!("模型输出: {action:?}");
+        i = i + 1;
+    }
+    Ok(())
+}
 
 use std::time::Instant;
 
-fn main() -> Result<()> {
-    const N: u32 = 1000;
+fn main1() -> Result<()> {
+    const N: u32 = 500;
     let mut total_infer = std::time::Duration::ZERO;
 
     for _ in 0..N {

src/policy.rs

@@ -64,5 +64,8 @@ pub fn policy(observation: [f32; 36]) -> Result<[f32; 8]> {
 
     let mut result = [0.0f32; 8];
     result.copy_from_slice(values);
+    result
+        .iter_mut()
+        .for_each(|value| *value = (*value * 0.5).clamp(-1.57, 1.57));
     Ok(result)
 }