Reinforcement Learning (RL) requires many interactions with the environment to converge to an optimal strategy, which makes it unfeasible to apply to wheel loaders and the bucket filling problem without using simulators. However, it is difficult to model the pile dynamics in the simulator because of unknown parameters, which results in poor transferability from the simulation to the real environment. Instead, this paper uses world models, serving as a fast surrogate simulator, creating a dream environment where a reinforcement learning (RL) agent explores and optimizes its bucket-filling behavior. The trained agent is then deployed on a full-size wheel loader without modifications, demonstrating its ability to outperform the previous benchmark controller, which was synthesized using imitation learning. Additionally, the same performance was observed as that of a controller pre-trained with imitation learning and optimized on the test pile using RL.

中文翻译：

---

在梦想环境中优化轮式装载机的铲斗填充策略


强化学习 （RL） 需要与环境进行多次交互才能收敛到最佳策略，这使得在不使用模拟器的情况下应用于轮式装载机和铲斗填充问题是不可行的。然而，由于参数未知，很难在模拟器中对桩动力学进行建模，导致从模拟到真实环境的可传递性差。相反，本文使用世界模型作为快速代理模拟器，创建一个梦幻环境，强化学习 （RL） 代理在其中探索和优化其桶装行为。然后，将经过训练的代理部署在全尺寸轮式装载机上，无需修改，证明其性能优于之前使用模仿学习合成的基准控制器。此外，观察到的性能与使用模仿学习进行预训练并使用 RL 在测试桩上优化的控制器的性能相同。