add no gui, no realtime mode, and train bash script

.gitignore

@@ -10,3 +10,13 @@ poetry.toml
 **/log/
 *.spec
 dist/
+*steps.zip
+*.pkl
+best_model.zip
+*.csv
+*.npz
+*.xml
+*.json
+*.yaml
+*.iml
+*.TXT

command.md

@@ -0,0 +1,14 @@
+训练（默认）
+bash train.sh
+
+测试（实时+显示画面)
+GYM_CPU_MODE=test GYM_CPU_TEST_MODEL=scripts/gyms/logs/Walk_R0_005/best_model.zip GYM_CPU_TEST_FOLDER=scripts/gyms/logs/Walk_R0_005/ GYM_CPU_TEST_NO_RENDER=0 GYM_CPU_TEST_NO_REALTIME=0 bash train.sh
+
+测试（无画面、非实时）
+GYM_CPU_MODE=test GYM_CPU_TEST_NO_RENDER=1 GYM_CPU_TEST_NO_REALTIME=1 bash train.sh
+
+retrain（继续训练）
+GYM_CPU_MODE=train GYM_CPU_TRAIN_MODEL=scripts/gyms/logs/Walk_R0_005/best_model.zip bash train.sh
+
+retrain+改训练超参
+GYM_CPU_MODE=train GYM_CPU_TRAIN_MODEL=scripts/gyms/logs/Walk_R0_004/best_model.zip GYM_CPU_TRAIN_LR=2e-4 GYM_CPU_TRAIN_BATCH_SIZE=256 GYM_CPU_TRAIN_EPOCHS=8 bash train.sh

communication/server.py

@@ -1,5 +1,6 @@
 import logging
 import socket
+import time
 from select import select
 from communication.world_parser import WorldParser
 
@@ -10,15 +11,27 @@ class Server:
     def __init__(self, host: str, port: int, world_parser: WorldParser):
         self.world_parser: WorldParser = world_parser
         self.__host: str = host
-        self.__port: str = port
-        self.__socket: socket = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
-        self.__socket.setsockopt(socket.IPPROTO_TCP, socket.TCP_NODELAY, 1)
+        self.__port: int = port
+        self.__socket: socket.socket = self._create_socket()
         self.__send_buff = []
         self.__rcv_buffer_size = 1024
         self.__rcv_buffer = bytearray(self.__rcv_buffer_size)
 
+    def _create_socket(self) -> socket.socket:
+        sock = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
+        sock.setsockopt(socket.IPPROTO_TCP, socket.TCP_NODELAY, 1)
+        return sock
+
     def connect(self) -> None:
         logger.info("Connecting to server at %s:%d...", self.__host, self.__port)
+
+        # Always reconnect with a fresh socket object.
+        try:
+            self.__socket.close()
+        except OSError:
+            pass
+        self.__socket = self._create_socket()
+
         while True:
             try:
                 self.__socket.connect((self.__host, self.__port))
@@ -27,12 +40,19 @@ class Server:
                 logger.error(
                     "Connection refused. Make sure the server is running and listening on {self.__host}:{self.__port}."
                 )
+                time.sleep(0.05)
 
         logger.info(f"Server connection established to {self.__host}:{self.__port}.")
 
     def shutdown(self) -> None:
-        self.__socket.close()
+        try:
             self.__socket.shutdown(socket.SHUT_RDWR)
+        except OSError:
+            pass
+        try:
+            self.__socket.close()
+        except OSError:
+            pass
 
     def send_immediate(self, msg: str) -> None:
         """

scripts/commons/Server.py

@@ -1,9 +1,10 @@
 import subprocess
 import os
+import time
 
 
 class Server():
-    def __init__(self, first_server_p, first_monitor_p, n_servers) -> None:
+    def __init__(self, first_server_p, first_monitor_p, n_servers, no_render=True, no_realtime=True) -> None:
         try:
             import psutil
             self.check_running_servers(psutil, first_server_p, first_monitor_p, n_servers)
@@ -17,21 +18,32 @@ class Server():
 
         # makes it easier to kill test servers without affecting train servers
         cmd = "rcssservermj"
+        render_arg = "--no-render" if no_render else ""
+        realtime_arg = "--no-realtime" if no_realtime else ""
         for i in range(n_servers):
             port = first_server_p + i
             mport = first_monitor_p + i
 
-            server_cmd = f"{cmd} --aport {port} --mport {mport} "
+            server_cmd = f"{cmd} -c {port} -m {mport} {render_arg} {realtime_arg}".strip()
 
-            self.rcss_processes.append(
-                subprocess.Popen(
+            proc = subprocess.Popen(
                 server_cmd.split(),
                 stdout=subprocess.DEVNULL,
                 stderr=subprocess.STDOUT,
                 start_new_session=True
             )
+
+            # Avoid startup storm when launching many servers at once.
+            time.sleep(0.03)
+
+            rc = proc.poll()
+            if rc is not None:
+                raise RuntimeError(
+                    f"rcssservermj exited early (code={rc}) on server port {port}, monitor port {mport}"
                 )
 
+            self.rcss_processes.append(proc)
+
     def check_running_servers(self, psutil, first_server_p, first_monitor_p, n_servers):
         ''' Check if any server is running on chosen ports '''
         found = False

scripts/gyms/Walk.py

@@ -7,7 +7,8 @@ from random import random
 from random import uniform
 
 from stable_baselines3 import PPO
-from stable_baselines3.common.vec_env import SubprocVecEnv
+from stable_baselines3.common.monitor import Monitor
+from stable_baselines3.common.vec_env import SubprocVecEnv, DummyVecEnv
 
 import gymnasium as gym
 from gymnasium import spaces
@@ -50,6 +51,7 @@ class WalkEnv(gym.Env):
         self.waypoint_index = 0
         self.route_completed = False
         self.debug_every_n_steps = 5
+        self.enable_debug_joint_status = False
         self.calibrate_nominal_from_neutral = True
         self.auto_calibrate_train_sim_flip = True
         self.nominal_calibrated_once = False
@@ -57,7 +59,7 @@ class WalkEnv(gym.Env):
         self._target_hz = 0.0
         self._target_dt = 0.0
         self._last_sync_time = None
-        target_hz_env = 1000
+        target_hz_env = 0
         if target_hz_env:
             try:
                 self._target_hz = float(target_hz_env)
@@ -114,7 +116,6 @@ class WalkEnv(gym.Env):
                 0.0,
             ]
         )
-        self.reference_joint_nominal_position = self.joint_nominal_position.copy()
         self.joint_nominal_position = np.zeros(self.no_of_actions)
         self.train_sim_flip = np.array(
             [
@@ -144,9 +145,16 @@ class WalkEnv(gym.Env):
             ]
         )
 
-        self.scaling_factor = 0.5
+        self.scaling_factor = 0.3
         # self.scaling_factor = 1
 
+        # Small reset perturbations for robustness training.
+        self.enable_reset_perturb = True
+        self.reset_beam_yaw_range_deg = 180  # randomize target direction fully to encourage learning a real walk instead of a fixed gait
+        self.reset_joint_noise_rad = 0.015
+        self.reset_perturb_steps = 3
+        self.reset_recover_steps = 8
+
         self.previous_action = np.zeros(len(self.Player.robot.ROBOT_MOTORS))
         self.last_action_for_reward = np.zeros(len(self.Player.robot.ROBOT_MOTORS))
         self.previous_pos = np.array([0.0, 0.0])  # Track previous position
@@ -155,6 +163,33 @@ class WalkEnv(gym.Env):
         self.Player.server.send_immediate(
             f"(init {self.Player.robot.name} {self.Player.world.team_name} {self.Player.world.number})"
         )
+        self.start_time = time.time()
+
+    def _reconnect_server(self):
+        try:
+            self.Player.server.shutdown()
+        except Exception:
+            pass
+
+        self.Player.server.connect()
+        self.Player.server.send_immediate(
+            f"(init {self.Player.robot.name} {self.Player.world.team_name} {self.Player.world.number})"
+        )
+
+    def _safe_receive_world_update(self, retries=1):
+        last_exc = None
+        for attempt in range(retries + 1):
+            try:
+                self.Player.server.receive()
+                self.Player.world.update()
+                return
+            except (ConnectionResetError, OSError) as exc:
+                last_exc = exc
+                if attempt >= retries:
+                    raise
+                self._reconnect_server()
+        if last_exc is not None:
+            raise last_exc
 
     def debug_log(self, message):
         print(message)
@@ -165,45 +200,6 @@ class WalkEnv(gym.Env):
         except OSError:
             pass
 
-    def calibrate_train_sim_flip_from_neutral(self, neutral_joint_positions):
-        updated_flip = self.train_sim_flip.copy()
-        changed = []
-
-        for idx, (reference_value, observed_value) in enumerate(
-                zip(self.reference_joint_nominal_position, neutral_joint_positions)
-        ):
-            if idx >= 10:
-                continue
-            if abs(reference_value) < 0.15 or abs(observed_value) < 0.15:
-                continue
-
-            inferred_flip = 1.0 if np.sign(reference_value) == np.sign(observed_value) else -1.0
-            if updated_flip[idx] != inferred_flip:
-                changed.append((idx, updated_flip[idx], inferred_flip))
-                updated_flip[idx] = inferred_flip
-
-        self.train_sim_flip = updated_flip
-
-        if changed:
-            self.debug_log(
-                "[FlipDebug] "
-                f"changes={[(idx, old, new) for idx, old, new in changed]}"
-            )
-
-    def is_reliable_neutral_pose(self, neutral_joint_positions):
-        leg_positions = neutral_joint_positions[11:]
-        leg_norm = float(np.linalg.norm(leg_positions))
-        leg_max = float(np.max(np.abs(leg_positions)))
-        height = float(self.Player.world.global_position[2])
-
-        reliable = (
-                leg_norm > 0.8
-                and leg_max > 0.35
-                and 0.12 < height < 0.8
-        )
-
-        return reliable, leg_norm, leg_max, height
-
     def observe(self, init=False):
 
         """获取当前观测值"""
@@ -262,8 +258,7 @@ class WalkEnv(gym.Env):
 
     def sync(self):
         ''' Run a single simulation step '''
-        self.Player.server.receive()
-        self.Player.world.update()
+        self._safe_receive_world_update(retries=1)
         self.Player.robot.commit_motor_targets_pd()
         self.Player.server.send()
         if self._target_dt > 0.0:
@@ -301,6 +296,7 @@ class WalkEnv(gym.Env):
             f"err_norm={float(np.linalg.norm(joint_error)):.4f} "
             f"fallen={self.Player.world.global_position[2] < 0.3}"
         )
+        print(f"waist target={target_joint_positions[10]:.3f}, actual={actual_joint_positions[10]:.3f}")
 
     def reset(self, seed=None, options=None):
         '''
@@ -312,9 +308,9 @@ class WalkEnv(gym.Env):
         if seed is not None:
             np.random.seed(seed)
 
-        length1 = np.random.uniform(10, 20)  # randomize target distance
-        length2 = np.random.uniform(10, 20)  # randomize target distance
-        length3 = np.random.uniform(10, 20)  # randomize target distance
+        length1 = 2  # randomize target distance
+        length2 = np.random.uniform(0.6, 1)  # randomize target distance
+        length3 = np.random.uniform(0.6, 1)  # randomize target distance
         angle2 = np.random.uniform(-30, 30)  # randomize initial orientation
         angle3 = np.random.uniform(-30, 30)  # randomize target direction
 
@@ -329,64 +325,65 @@ class WalkEnv(gym.Env):
         # 随机 beam 目标位置和朝向，增加训练多样性
         beam_x = (random() - 0.5) * 10
         beam_y = (random() - 0.5) * 10
+        beam_yaw = uniform(-self.reset_beam_yaw_range_deg, self.reset_beam_yaw_range_deg)
 
         for _ in range(5):
-            self.Player.server.receive()
-            self.Player.world.update()
+            self._safe_receive_world_update(retries=2)
             self.Player.robot.commit_motor_targets_pd()
-            self.Player.server.commit_beam(pos2d=(beam_x, beam_y), rotation=0)
+            self.Player.server.commit_beam(pos2d=(beam_x, beam_y), rotation=beam_yaw)
             self.Player.server.send()
 
         # 执行 Neutral 技能直到完成，给机器人足够时间在 beam 位置稳定站立
         finished_count = 0
-        for _ in range(10):
+        for _ in range(50):
             finished = self.Player.skills_manager.execute("Neutral")
             self.sync()
             if finished:
                 finished_count += 1
-                if finished_count >= 3:  # 假设需要连续3次完成才算成功
+                if finished_count >= 20:  # 假设需要连续20次完成才算成功
                     break
 
-        # neutral_joint_positions = np.deg2rad(
-        #     [self.Player.robot.motor_positions[motor] for motor in self.Player.robot.ROBOT_MOTORS]
-        # )
-        # reliable_neutral, neutral_leg_norm, neutral_leg_max, neutral_height = self.is_reliable_neutral_pose(neutral_joint_positions)
+        if self.enable_reset_perturb and self.reset_joint_noise_rad > 0.0:
+            perturb_action = np.zeros(self.no_of_actions, dtype=np.float32)
+            # Perturb waist + lower body only (10:), keep head/arms stable.
+            perturb_action[10:] = np.random.uniform(
+                -self.reset_joint_noise_rad,
+                self.reset_joint_noise_rad,
+                size=(self.no_of_actions - 10,)
+            )
 
-        # if self.auto_calibrate_train_sim_flip and reliable_neutral and not self.flip_calibrated_once:
-        #     self.calibrate_train_sim_flip_from_neutral(neutral_joint_positions)
-        #     self.flip_calibrated_once = True
-        # if self.calibrate_nominal_from_neutral and reliable_neutral and not self.nominal_calibrated_once:
-        #     self.joint_nominal_position = neutral_joint_positions * self.train_sim_flip
-        #     self.nominal_calibrated_once = True
-        # self.debug_log(
-        #     "[ResetDebug] "
-        #     f"neutral_pos={np.round(self.Player.world.global_position, 3).tolist()} "
-        #     f"shoulders={np.round(neutral_joint_positions[2:10], 3).tolist()} "
-        #     f"legs={np.round(neutral_joint_positions[11:], 3).tolist()} "
-        #     f"flip={self.train_sim_flip.tolist()} "
-        #     f"nominal_legs={np.round(self.joint_nominal_position[11:], 3).tolist()} "
-        #     f"calibrated_once={(self.flip_calibrated_once, self.nominal_calibrated_once)} "
-        #     f"reliable_neutral={reliable_neutral} "
-        #     f"leg_norm={neutral_leg_norm:.3f} leg_max={neutral_leg_max:.3f} height={neutral_height:.3f}"
-        # )
+            for _ in range(self.reset_perturb_steps):
+                target_joint_positions = (self.joint_nominal_position + perturb_action) * self.train_sim_flip
+                for idx, target in enumerate(target_joint_positions):
+                    r.set_motor_target_position(
+                        r.ROBOT_MOTORS[idx], target * 180 / math.pi, kp=25, kd=0.6
+                    )
+                self.sync()
 
-        # reset_action_noise = np.random.uniform(-0.015, 0.015, size=(len(self.Player.robot.ROBOT_MOTORS),))
-        # self.target_joint_positions = (self.joint_nominal_position + reset_action_noise) * self.train_sim_flip
-
-        # for idx, target in enumerate(self.target_joint_positions):
-        #     r.set_motor_target_position(
-        #         r.ROBOT_MOTORS[idx], target*180/math.pi, kp=25, kd=0.6
-        #     )
+            for i in range(self.reset_recover_steps):
+                # Linearly fade perturbation to help policy start from near-neutral.
+                alpha = 1.0 - float(i + 1) / float(self.reset_recover_steps)
+                target_joint_positions = (self.joint_nominal_position + alpha * perturb_action) * self.train_sim_flip
+                for idx, target in enumerate(target_joint_positions):
+                    r.set_motor_target_position(
+                        r.ROBOT_MOTORS[idx], target * 180 / math.pi, kp=25, kd=0.6
+                    )
+                self.sync()
 
         # memory variables
+        self.sync()  
         self.initial_position = np.array(self.Player.world.global_position[:2])
         self.previous_pos = self.initial_position.copy()  # Critical: set to actual position
         self.act = np.zeros(self.no_of_actions, np.float32)
-        point1 = self.initial_position + np.array([length1, 0])
+        # Build target in the robot's current forward direction instead of fixed global +x.
+        heading_deg = float(r.global_orientation_euler[2])
+        forward_offset = MathOps.rotate_2d_vec(np.array([length1, 0.0]), heading_deg, is_rad=False)
+        point1 = self.initial_position + forward_offset
         point2 = point1 + MathOps.rotate_2d_vec(np.array([length2, 0]), angle2, is_rad=False)
         point3 = point2 + MathOps.rotate_2d_vec(np.array([length3, 0]), angle3, is_rad=False)
-        self.point_list = [point1, point2, point3]
+        self.point_list = [point1]
         self.target_position = self.point_list[self.waypoint_index]
+        self.initial_height = self.Player.world.global_position[2]
 
         return self.observe(True), {}
 
@@ -394,89 +391,99 @@ class WalkEnv(gym.Env):
         return
 
     def compute_reward(self, previous_pos, current_pos, action):
-        eps = 1e-6
-        dt = 0.05
-
-        velocity = current_pos - previous_pos
-        speed_step = float(np.linalg.norm(velocity))
-        speed = speed_step / dt
-
-        direction_to_target = self.target_position - current_pos
-        prev_direction_to_target = self.target_position - previous_pos
-        distance_to_target = float(np.linalg.norm(direction_to_target))
-        prev_distance_to_target = float(np.linalg.norm(prev_direction_to_target))
-
-        # Progress toward waypoint (secondary signal)
-        progress = prev_distance_to_target - distance_to_target
-        progress_reward = np.clip(progress * 2.0, -1.5, 2.5)
-
-        # Forward speed and lateral drift
-        forward_dir = direction_to_target / max(distance_to_target, eps)
-        forward_speed = float(np.dot(velocity, forward_dir)) / dt
-        target_speed = 1.0
-        speed_error = forward_speed - target_speed
-        speed_reward = 3.0 * math.exp(-1.5 * (speed_error ** 2))
-
-        lateral_vec = velocity - forward_dir * np.dot(velocity, forward_dir)
-        lateral_speed = float(np.linalg.norm(lateral_vec)) / dt
-        lateral_penalty = -0.6 * np.clip(lateral_speed, 0.0, 2.0)
-
-        # Heading alignment (small shaping term)
-        if speed_step > 1e-4 and distance_to_target > 1e-4:
-            directional_alignment = np.dot(velocity, direction_to_target) / (speed_step * distance_to_target)
-            directional_alignment = float(np.clip(directional_alignment, -1.0, 1.0))
-            direction_reward = max(0.0, directional_alignment) * 0.3
-        else:
-            direction_reward = 0.0
-
-        alive_bonus = 0.05
-
-        # Height and posture
         height = float(self.Player.world.global_position[2])
-        if 0.8 <= height <= 1.05:
-            height_reward = 1.0
-        elif 0.40 <= height <= 1.20:
-            height_reward = -1.0
-        else:
-            height_reward = -6.0
 
         orientation_quat_inv = R.from_quat(self.Player.robot._global_cheat_orientation).inv()
         projected_gravity = orientation_quat_inv.apply(np.array([0.0, 0.0, -1.0]))
         tilt_mag = float(np.linalg.norm(projected_gravity[:2]))
-        posture_penalty = -2.2 * (tilt_mag ** 2)
+        ang_vel = np.deg2rad(self.Player.robot.gyroscope)
+        ang_vel_mag = float(np.linalg.norm(ang_vel))
 
-        motionless_penalty = -1.5 if speed < 0.1 else 0.0
+        is_fallen = height < 0.3
+        if is_fallen:
+            # remain = max(0, 800 - self.step_counter)
+            # return -8.0 - 0.01 * remain
+            return -1.0
         
-        # Waypoint bonus
-        waypoint_bonus = 0.0
-        if distance_to_target < 0.5:
-            waypoint_bonus = 25.0
-            if self.waypoint_index < len(self.point_list) - 1:
-                self.waypoint_index += 1
-                self.target_position = self.point_list[self.waypoint_index]
-            else:
-                waypoint_bonus = 100.0
-                self.route_completed = True
 
-        # Effort + smoothness
-        action_magnitude = float(np.linalg.norm(action[11:]))
-        action_penalty = -0.05 * action_magnitude
-        action_delta = action - self.last_action_for_reward
-        smoothness_penalty = -0.02 * float(np.linalg.norm(action_delta[11:]))
 
-        return (
-                progress_reward
-                + speed_reward
-                + lateral_penalty
-                + direction_reward
-                + alive_bonus
-                + height_reward
-                + posture_penalty
-                + motionless_penalty
-                + waypoint_bonus
-                + action_penalty
-                + smoothness_penalty
+        # # 目标方向
+        # to_target = self.target_position - current_pos
+        # dist_to_target = float(np.linalg.norm(to_target))
+        # if dist_to_target < 0.5:
+        #     return 15.0
+
+        # forward_dir = to_target / dist_to_target if dist_to_target > 0.1 else np.array([1.0, 0.0])
+        # delta_pos = current_pos - previous_pos
+        # forward_step = float(np.dot(delta_pos, forward_dir))
+        # lateral_step = float(np.linalg.norm(delta_pos - forward_dir * forward_step))
+
+        # 奖励项
+        # progress_reward = 2 * forward_step
+        # lateral_penalty = -0.1 * lateral_step
+        alive_bonus = 2.0
+
+        # action_penalty = -0.01 * float(np.linalg.norm(action))
+        smoothness_penalty = -0.01 * float(np.linalg.norm(action - self.last_action_for_reward))
+
+        posture_penalty = -0.3 * (tilt_mag)
+        ang_vel_penalty = -0.02 * ang_vel_mag
+
+        target_height = self.initial_height
+        height_error =  height - target_height
+        height_penalty = -0.5 * abs(height_error)  # 惩罚高度偏离，系数可调
+
+        # # 在 compute_reward 开头附近，添加高度变化率计算
+        # if not hasattr(self, 'last_height'):
+        #     self.last_height = height
+        #     self.last_height_time = self.step_counter  # 可选，用于时间间隔
+        # height_rate = height - self.last_height  # 正为上升，负为下降
+        # self.last_height = height
+
+        # 惩罚高度下降（负变化率）
+        # height_down_penalty = -5.0 * max(0, -height_rate)  # 系数可调，-height_rate 为正表示下降幅度
+
+        # # 在 compute_reward 中
+        # if self.step_counter > 50:
+        #     avg_prev_action = np.mean(self.prev_action_history, axis=0)
+        #     novelty = float(np.linalg.norm(action - avg_prev_action))
+        #     exploration_bonus = 0.05 * novelty
+        # else:
+        #     exploration_bonus = 0
+
+        # self.prev_action_history[self.history_idx] = action
+        # self.history_idx = (self.history_idx + 1) % 50
+
+
+        total = (
+            # progress_reward  + 
+                 alive_bonus + 
+                 # lateral_penalty +
+                 # action_penalty +
+                smoothness_penalty +
+                 posture_penalty
+                 + ang_vel_penalty
+                 + height_penalty
+                #  + exploration_bonus
+                # + height_down_penalty
                  )
+        if time.time() - self.start_time >= 1200:
+            self.start_time = time.time()
+            print(
+                #   f"progress_reward:{progress_reward:.4f}",
+                #   f"lateral_penalty:{lateral_penalty:.4f}",
+                #   f"action_penalty:{action_penalty:.4f}"s, 
+                  f"height_penalty:{height_penalty:.4f}",
+                  f"smoothness_penalty:{smoothness_penalty:.4f},",
+                  f"posture_penalty:{posture_penalty:.4f}",
+                #   f"ang_vel_penalty:{ang_vel_penalty:.4f}",
+                #   f"height_down_penalty:{height_down_penalty:.4f}",
+                #   f"exploration_bonus:{exploration_bonus:.4f}"
+            )
+
+        return total
+
+
 
     def step(self, action):
 
@@ -484,21 +491,23 @@ class WalkEnv(gym.Env):
         self.previous_action = action
 
         self.target_joint_positions = (
-                self.joint_nominal_position
-                + self.scaling_factor * action
+                # self.joint_nominal_position +
+                 self.scaling_factor * action
         )
         self.target_joint_positions *= self.train_sim_flip
 
         for idx, target in enumerate(self.target_joint_positions):
             r.set_motor_target_position(
-                r.ROBOT_MOTORS[idx], target * 180 / math.pi, kp=25, kd=0.6
+                r.ROBOT_MOTORS[idx], target * 180 / math.pi, kp=40, kd=1.0
             )
 
+        self.previous_action = action
+
         self.sync()  # run simulation step
         self.step_counter += 1
 
-        # if self.step_counter % self.debug_every_n_steps == 0:
-        #     self.debug_joint_status()
+        if self.enable_debug_joint_status and self.step_counter % self.debug_every_n_steps == 0:
+            self.debug_joint_status()
 
         current_pos = np.array(self.Player.world.global_position[:2], dtype=np.float32)
 
@@ -526,13 +535,14 @@ class Train(Train_Base):
     def train(self, args):
 
         # --------------------------------------- Learning parameters
-        n_envs = 20  # Reduced from 8 to decrease CPU/network pressure during init
+        n_envs = int(os.environ.get("GYM_CPU_N_ENVS", "20"))
         if n_envs < 1:
             raise ValueError("GYM_CPU_N_ENVS must be >= 1")
-        n_steps_per_env = 512  # RolloutBuffer is of size (n_steps_per_env * n_envs)
-        minibatch_size = 128  # should be a factor of (n_steps_per_env * n_envs)
+        server_warmup_sec = float(os.environ.get("GYM_CPU_SERVER_WARMUP_SEC", "3.0"))
+        n_steps_per_env = int(os.environ.get("GYM_CPU_TRAIN_STEPS_PER_ENV", "256"))  # RolloutBuffer is of size (n_steps_per_env * n_envs)
+        minibatch_size = int(os.environ.get("GYM_CPU_TRAIN_BATCH_SIZE", "512"))  # should be a factor of (n_steps_per_env * n_envs)
         total_steps = 30000000
-        learning_rate = 2e-4
+        learning_rate = float(os.environ.get("GYM_CPU_TRAIN_LR", "3e-4"))
         folder_name = f'Walk_R{self.robot_type}'
         model_path = f'./scripts/gyms/logs/{folder_name}/'
 
@@ -540,22 +550,29 @@ class Train(Train_Base):
         print(f"Using {n_envs} parallel environments")
 
         # --------------------------------------- Run algorithm
-        def init_env(i_env):
+        def init_env(i_env, monitor=False):
             def thunk():
-                return WalkEnv(self.ip, self.server_p + i_env)
+                env = WalkEnv(self.ip, self.server_p + i_env)
+                if monitor:
+                    env = Monitor(env)
+                return env
 
             return thunk
 
         server_log_dir = os.path.join(model_path, "server_logs")
         os.makedirs(server_log_dir, exist_ok=True)
-        servers = Train_Server(self.server_p, self.monitor_p_1000, n_envs + 1)  # include 1 extra server for testing
+        servers = Train_Server(self.server_p, self.monitor_p_1000, n_envs + 1, no_render=True, no_realtime=True)  # include 1 extra server for testing
 
         # Wait for servers to start
         print(f"Starting {n_envs + 1} rcssservermj servers...")
+        if server_warmup_sec > 0:
+            print(f"Waiting {server_warmup_sec:.1f}s for server warmup...")
+            sleep(server_warmup_sec)
         print("Servers started, creating environments...")
 
-        env = SubprocVecEnv([init_env(i) for i in range(n_envs)])
-        eval_env = SubprocVecEnv([init_env(n_envs)])
+        env = SubprocVecEnv([init_env(i, monitor=True) for i in range(n_envs)])
+        # Use single-process eval env to avoid extra subprocess fragility during callback evaluation.
+        eval_env = DummyVecEnv([init_env(n_envs, monitor=True)])
 
         try:
             # Custom policy network architecture
@@ -580,14 +597,17 @@ class Train(Train_Base):
                     learning_rate=learning_rate,
                     device="cpu",
                     policy_kwargs=policy_kwargs,
-                    # ent_coef=0.01,  # Entropy coefficient for exploration
-                    # clip_range=0.2,  # PPO clipping parameter
-                    # gae_lambda=0.95,  # GAE lambda
-                    # gamma=0.99  # Discount factor
+                    ent_coef=float(os.environ.get("GYM_CPU_TRAIN_ENT_COEF", "0.05")),  # Entropy coefficient for exploration
+                    clip_range=float(os.environ.get("GYM_CPU_TRAIN_CLIP_RANGE", "0.2")),  # PPO clipping parameter
+                    gae_lambda=0.95,  # GAE lambda
+                    gamma=float(os.environ.get("GYM_CPU_TRAIN_GAMMA", "0.95")), # Discount factor
+                    target_kl=0.03,
+                    n_epochs=int(os.environ.get("GYM_CPU_TRAIN_EPOCHS", "5")),
+                    # tensorboard_log=f"./scripts/gyms/logs/{folder_name}/tensorboard/"
                 )
 
             model_path = self.learn_model(model, total_steps, model_path, eval_env=eval_env,
-                                          eval_freq=n_steps_per_env * 10, save_freq=n_steps_per_env * 10,
+                                          eval_freq=n_steps_per_env * 20, save_freq=n_steps_per_env * 20,
                                           backup_env_file=__file__)
         except KeyboardInterrupt:
             sleep(1)  # wait for child processes
@@ -604,7 +624,16 @@ class Train(Train_Base):
         # Uses different server and monitor ports
         server_log_dir = os.path.join(args["folder_dir"], "server_logs")
         os.makedirs(server_log_dir, exist_ok=True)
-        server = Train_Server(self.server_p - 1, self.monitor_p, 1)
+        test_no_render = os.environ.get("GYM_CPU_TEST_NO_RENDER", "0") == "1"
+        test_no_realtime = os.environ.get("GYM_CPU_TEST_NO_REALTIME", "0") == "1"
+
+        server = Train_Server(
+            self.server_p - 1,
+            self.monitor_p,
+            1,
+            no_render=test_no_render,
+            no_realtime=test_no_realtime,
+        )
         env = WalkEnv(self.ip, self.server_p - 1)
         model = PPO.load(args["model_file"], env=env)
 
@@ -635,6 +664,16 @@ if __name__ == "__main__":
     )
 
     trainer = Train(script_args)
+
+    run_mode = os.environ.get("GYM_CPU_MODE", "train").strip().lower()
+
+    if run_mode == "test":
+        test_model_file = os.environ.get("GYM_CPU_TEST_MODEL", "scripts/gyms/logs/Walk_R0_004/best_model.zip")
+        test_folder = os.environ.get("GYM_CPU_TEST_FOLDER", "scripts/gyms/logs/Walk_R0_004/")
+        trainer.test({"model_file": test_model_file, "folder_dir": test_folder})
+    else:
+        retrain_model = os.environ.get("GYM_CPU_TRAIN_MODEL", "").strip()
+        if retrain_model:
+            trainer.train({"model_file": retrain_model})
+        else:
             trainer.train({})
-    # trainer.test({"model_file": "scripts/gyms/logs/Walk_R0_003/best_model.zip",
-    #               "folder_dir": "Walk_R0_003",})

train.sh

@@ -0,0 +1,126 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+# ------------------------------
+# 资源限制配置（cgroup v2 + systemd-run）
+# ------------------------------
+# 说明：
+# 1) 这个脚本会把训练进程放进一个临时的 systemd scope 中，并施加 CPU/内存上限。
+# 2) 仅限制“本次训练进程”，不会永久改系统配置。
+# 3) 下面变量都支持“环境变量覆盖”，即你可以在命令前临时指定。
+#
+# CPU 核数基准（默认 20）：
+# 例如你的机器按 20 核预算来算，可保持默认。
+CORES="${CORES:-20}"
+# CPU 占用百分比（默认 95）：
+# 最终会与 CORES 相乘得到 CPUQuota。
+# 例：CORES=20, UTIL_PERCENT=95 -> CPUQuota=1900%（约 19 核等效）
+UTIL_PERCENT="${UTIL_PERCENT:-95}"
+CPU_QUOTA="$((CORES * UTIL_PERCENT))%"
+
+# 内存上限（默认 28G）：
+# 可改成 16G、24G 等，避免训练把系统内存吃满。
+MEMORY_MAX="${MEMORY_MAX:-28G}"
+
+# ------------------------------
+# 训练运行参数（由 scripts/gyms/Walk.py 读取）
+# ------------------------------
+# 运行模式：train 或 test
+GYM_CPU_MODE="${GYM_CPU_MODE:-train}"
+
+# 并行环境数量：越大通常吞吐越高，但也更容易触发服务器连接不稳定。
+# 建议从 8~12 起步，稳定后再升到 16/20。
+GYM_CPU_N_ENVS="${GYM_CPU_N_ENVS:-20}"
+# 服务器预热时间（秒）：
+# 在批量拉起 rcssserver 后等待一段时间，再创建 SubprocVecEnv，
+# 可降低 ConnectionReset/EOFError 概率。
+GYM_CPU_SERVER_WARMUP_SEC="${GYM_CPU_SERVER_WARMUP_SEC:-10}"
+
+# 训练专用参数
+GYM_CPU_TRAIN_STEPS_PER_ENV="${GYM_CPU_TRAIN_STEPS_PER_ENV:-256}"
+GYM_CPU_TRAIN_BATCH_SIZE="${GYM_CPU_TRAIN_BATCH_SIZE:-512}"
+GYM_CPU_TRAIN_LR="${GYM_CPU_TRAIN_LR:-1e-4}"
+GYM_CPU_TRAIN_ENT_COEF="${GYM_CPU_TRAIN_ENT_COEF:-0.03}"
+GYM_CPU_TRAIN_CLIP_RANGE="${GYM_CPU_TRAIN_CLIP_RANGE:-0.13}"
+GYM_CPU_TRAIN_GAMMA="${GYM_CPU_TRAIN_GAMMA:-0.95}"
+GYM_CPU_TRAIN_EPOCHS="${GYM_CPU_TRAIN_EPOCHS:-5}"
+GYM_CPU_TRAIN_MODEL="${GYM_CPU_TRAIN_MODEL:-}"
+
+# 测试专用参数
+GYM_CPU_TEST_MODEL="${GYM_CPU_TEST_MODEL:-scripts/gyms/logs/Walk_R0_004/best_model.zip}"
+GYM_CPU_TEST_FOLDER="${GYM_CPU_TEST_FOLDER:-scripts/gyms/logs/Walk_R0_004/}"
+# 测试默认实时且显示画面：默认均为 0
+# 设为 1 表示关闭对应能力
+GYM_CPU_TEST_NO_RENDER="${GYM_CPU_TEST_NO_RENDER:-0}"
+GYM_CPU_TEST_NO_REALTIME="${GYM_CPU_TEST_NO_REALTIME:-0}"
+
+# Python 解释器选择策略：
+# 1) 优先使用你手动传入的 PYTHON_BIN
+# 2) 其次用当前激活 conda 环境（CONDA_PREFIX/bin/python）
+# 3) 再回退到默认 mujoco 环境路径
+# 4) 最后尝试系统 python / python3
+DEFAULT_PYTHON="/home/solren/Downloads/Anaconda/envs/mujoco/bin/python"
+CONDA_PYTHON="${CONDA_PREFIX:-}/bin/python"
+
+# 安全保护：不要用 sudo 运行。
+# 原因：sudo 可能导致 conda 环境与用户会话环境不一致，
+# 会引发 python 路径丢失、systemd --user 会话不可见等问题。
+if [[ "${EUID}" -eq 0 ]]; then
+	echo "Do not run this script with sudo; run as your normal user in conda env 'mujoco'."
+	exit 1
+fi
+
+# 解析最终使用的 Python 可执行文件。
+if [[ -n "${PYTHON_BIN:-}" ]]; then
+	PYTHON_EXEC="${PYTHON_BIN}"
+elif [[ -n "${CONDA_PREFIX:-}" && -x "${CONDA_PYTHON}" ]]; then
+	PYTHON_EXEC="${CONDA_PYTHON}"
+elif [[ -x "${DEFAULT_PYTHON}" ]]; then
+	PYTHON_EXEC="${DEFAULT_PYTHON}"
+elif command -v python >/dev/null 2>&1; then
+	PYTHON_EXEC="$(command -v python)"
+elif command -v python3 >/dev/null 2>&1; then
+	PYTHON_EXEC="$(command -v python3)"
+else
+	echo "No Python executable found. Set PYTHON_BIN=/abs/path/to/python and retry."
+	exit 1
+fi
+
+# 脚本所在目录（绝对路径），便于后续定位模块/相对路径。
+SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
+
+# 打印当前生效配置，方便排障和复现实验。
+echo "Starting training with limits: CPU=${CPU_QUOTA}, Memory=${MEMORY_MAX}"
+echo "Mode: ${GYM_CPU_MODE}"
+echo "Runtime knobs: GYM_CPU_N_ENVS=${GYM_CPU_N_ENVS}, GYM_CPU_SERVER_WARMUP_SEC=${GYM_CPU_SERVER_WARMUP_SEC}"
+echo "Using Python: ${PYTHON_EXEC}"
+if [[ -n "${CONDA_DEFAULT_ENV:-}" ]]; then
+	echo "Detected conda env: ${CONDA_DEFAULT_ENV}"
+fi
+
+# 使用 systemd-run --user --scope 启动“受限资源”的训练进程：
+# - CPUQuota: 总 CPU 配额
+# - MemoryMax: 最大内存
+# - env ...  : 显式传递训练参数到 Python 进程
+# - python -m scripts.gyms.Walk: 以模块方式启动训练入口
+systemd-run --user --scope \
+	-p CPUQuota="${CPU_QUOTA}" \
+	-p MemoryMax="${MEMORY_MAX}" \
+	env \
+	GYM_CPU_MODE="${GYM_CPU_MODE}" \
+	GYM_CPU_N_ENVS="${GYM_CPU_N_ENVS}" \
+	GYM_CPU_SERVER_WARMUP_SEC="${GYM_CPU_SERVER_WARMUP_SEC}" \
+	GYM_CPU_TRAIN_STEPS_PER_ENV="${GYM_CPU_TRAIN_STEPS_PER_ENV}" \
+	GYM_CPU_TRAIN_BATCH_SIZE="${GYM_CPU_TRAIN_BATCH_SIZE}" \
+	GYM_CPU_TRAIN_LR="${GYM_CPU_TRAIN_LR}" \
+	GYM_CPU_TRAIN_ENT_COEF="${GYM_CPU_TRAIN_ENT_COEF}" \
+	GYM_CPU_TRAIN_CLIP_RANGE="${GYM_CPU_TRAIN_CLIP_RANGE}" \
+	GYM_CPU_TRAIN_GAMMA="${GYM_CPU_TRAIN_GAMMA}" \
+	GYM_CPU_TRAIN_EPOCHS="${GYM_CPU_TRAIN_EPOCHS}" \
+	GYM_CPU_TRAIN_MODEL="${GYM_CPU_TRAIN_MODEL}" \
+	GYM_CPU_TEST_MODEL="${GYM_CPU_TEST_MODEL}" \
+	GYM_CPU_TEST_FOLDER="${GYM_CPU_TEST_FOLDER}" \
+	GYM_CPU_TEST_NO_RENDER="${GYM_CPU_TEST_NO_RENDER}" \
+	GYM_CPU_TEST_NO_REALTIME="${GYM_CPU_TEST_NO_REALTIME}" \
+	"${PYTHON_EXEC}" "-m" "scripts.gyms.Walk"
+

world/world.py

@@ -47,6 +47,7 @@ class World:
         self.their_team_players: list[OtherRobot] = [OtherRobot(is_teammate=False) for _ in
                                                      range(self.MAX_PLAYERS_PER_TEAM)]
         self.field: Field = self.__initialize_field(field_name=field_name)
+        self.WORLD_STEPTIME: float = 0.005  # Time step of the world in seconds
 
     def update(self) -> None:
         """