STAP: Sequencing Task-Agnostic Policies
Advances in robotic skill acquisition have made it possible to build general-purpose libraries of learned skills for downstream manipulation tasks. However, naively executing these skills one after the other is unlikely to succeed without accounting for dependencies between actions prevalent in long-horizon plans. We present Sequencing Task-Agnostic Policies (STAP), a scalable framework for training manipulation skills and coordinating their geometric dependencies at planning time to solve long-horizon tasks never seen by any skill during training. Given that Q-functions encode a measure of skill feasibility, we formulate an optimization problem to maximize the joint success of all skills sequenced in a plan, which we estimate by the product of their Q-values. Our experiments indicate that this objective function approximates ground truth plan feasibility and, when used as a planning objective, reduces myopic behavior and thereby promotes long-horizon task success. We further demonstrate how STAP can be used for task and motion planning by estimating the geometric feasibility of skill sequences provided by a task planner. We evaluate our approach in simulation and on a real robot. Qualitative results and code are made available at https://sites.google.com/stanford.edu/stap.
Code (1)
Tasks
Motion PlanningTask and Motion PlanningSimilar Papers 제목 키워드 기반
Whole genome single nucleotide polymorphism genotyping of Staphylococcus aureus
Next-generation sequencing technology enables routine detection of bacterial pathogens for clinical diagnostics and genetic research. Whole genome sequencing has been of importance in the epidemiologic analysis of bacter…
Using Deep Reinforcement Learning to Train and Evaluate Instructional Sequencing Policies for an Intelligent Tutoring System
We present STEP, a novel Deep Reinforcement Learning solution to the problem of learning instructional sequencing. STEP has three components: 1. Simulate the student by fitting a knowledge tracing model to data logged b…
Deep Reinforcement LearningKnowledge TracingAn Optimization Framework for Task Sequencing in Curriculum Learning
Curriculum learning in reinforcement learning is used to shape exploration by presenting the agent with increasingly complex tasks. The idea of curriculum learning has been largely applied in both animal training and ped…
reinforcement-learningReinforcement LearningReinforcement Learning (RL)Vehicle Sequencing at Signal-Free Intersections: Analytical Performance Guarantees Based on PDMP Formulation
Signal-free intersections are a representative application of smart and connected vehicle technologies. Although extensive results have been developed for trajectory planning and autonomous driving, the formulation and e…
Autonomous DrivingTrajectory PlanningStaPep: an open-source tool for the structure prediction and feature extraction of hydrocarbon-stapled peptides
Many tools exist for extracting structural and physiochemical descriptors from linear peptides to predict their properties, but similar tools for hydrocarbon-stapled peptides are lacking.Here, we present StaPep, a Python…
Retrieval