论文标题
以这些方式行走：调整机器人控制以泛化的行为多样性
Walk These Ways: Tuning Robot Control for Generalization with Multiplicity of Behavior
论文作者
论文摘要
学识渊博的运动策略可以迅速适应与训练过程中经历的不同环境，但在分布外测试环境中失败时缺乏快速调整的机制。这需要一个缓慢而迭代的奖励和环境重新设计的循环，以便在新任务上实现良好的绩效。作为替代方案，我们建议学习一项单一的政策，该政策编码一个结构化的运动策略家族，该策略以不同的方式解决训练任务，从而导致了多种行为（MOB）。不同的策略以不同的方式推广，可以实时选择新任务或环境，从而绕开了耗时的重新培训的需求。我们释放了一个快速，健壮的露天暴力控制器，步行这些方式，可以通过可变的脚挥手，姿势和速度执行多样的步态，从而解除了多样化的下游任务：蹲下，跳跃，高速跑步，楼梯横过，楼梯横过，对铲子，节奏舞蹈，节奏舞和更多。视频和代码发布：https：//gmargo11.github.io/walk-these-ways/
Learned locomotion policies can rapidly adapt to diverse environments similar to those experienced during training but lack a mechanism for fast tuning when they fail in an out-of-distribution test environment. This necessitates a slow and iterative cycle of reward and environment redesign to achieve good performance on a new task. As an alternative, we propose learning a single policy that encodes a structured family of locomotion strategies that solve training tasks in different ways, resulting in Multiplicity of Behavior (MoB). Different strategies generalize differently and can be chosen in real-time for new tasks or environments, bypassing the need for time-consuming retraining. We release a fast, robust open-source MoB locomotion controller, Walk These Ways, that can execute diverse gaits with variable footswing, posture, and speed, unlocking diverse downstream tasks: crouching, hopping, high-speed running, stair traversal, bracing against shoves, rhythmic dance, and more. Video and code release: https://gmargo11.github.io/walk-these-ways/
