论文标题
Dropo：带有离线域随机化的SIM到现实转移
DROPO: Sim-to-Real Transfer with Offline Domain Randomization
论文作者
论文摘要
近年来，作为动态参数的域随机化已经获得了很多吸引，作为在机器人操作中使用增强策略的SIM卡转移的一种方法。但是，找到最佳的随机分布可能很困难。在本文中，我们介绍了Dropo，这是一种用于估算安全SIM到真实传输的域随机分布的新方法。与先前的工作不同，Dropo仅需要有限的，预先收集的轨迹数据集，并明确地模拟参数不确定性，以使用基于似然的方法匹配真实数据。我们证明了Dropo能够在模拟中恢复动态参数分布，并找到能够补偿未建模现象的分布。我们还在两个零射击的SIM到运行传输方案中评估了该方法，显示了成功的域传输和改善先前方法的性能。
In recent years, domain randomization over dynamics parameters has gained a lot of traction as a method for sim-to-real transfer of reinforcement learning policies in robotic manipulation; however, finding optimal randomization distributions can be difficult. In this paper, we introduce DROPO, a novel method for estimating domain randomization distributions for safe sim-to-real transfer. Unlike prior work, DROPO only requires a limited, precollected offline dataset of trajectories, and explicitly models parameter uncertainty to match real data using a likelihood-based approach. We demonstrate that DROPO is capable of recovering dynamic parameter distributions in simulation and finding a distribution capable of compensating for an unmodeled phenomenon. We also evaluate the method in two zero-shot sim-to-real transfer scenarios, showing successful domain transfer and improved performance over prior methods.
