利用实时仿真的内在随机性促进机器人操纵的强化学习（英文版）

英文标题：Exploiting Intrinsic Stochasticity of Real-Time Simulation to Facilitate Robust Reinforcement Learning for Robot Manipulation中文摘要：使用实时模拟的本地随机性在强化学习中得到应用可以改善域随机化技术的性能和稳健性能，进而在机器人操作中实现更好的泛化和相对低的启发式随机化水平，解决了实际应用中如机器人操作的模拟到现实世界的差距问题。英文摘要：Simulation is essential to reinforcement learning (RL) before implementationin the real world, especially for safety-critical applications like robotmanipulation. Conventionally, RL agents are sensitive to the discrepanciesbetween the simulation and the real w