修改了算法代码,并建立了一个简单的训练脚本.修改bert处理二维输入,移除PPO的permute参数

Env/__init__.py

@@ -0,0 +1,15 @@
+"""
+Multi-Agent Scenario Environment
+
+多智能体场景环境
+"""
+
+from .scenario_env import MultiAgentScenarioEnv, PolicyVehicle
+from .simple_idm_policy import ConstantVelocityPolicy
+
+__all__ = [
+    'MultiAgentScenarioEnv',
+    'PolicyVehicle',
+    'ConstantVelocityPolicy',
+]
+