Broadly-Exploring, Local-Policy Trees for Long-Horizon Task Planning

10/13/2020
by   Brian Ichter, et al.
0

Long-horizon planning in realistic environments requires the ability to reason over sequential tasks in high-dimensional state spaces with complex dynamics. Classical motion planning algorithms, such as rapidly-exploring random trees, are capable of efficiently exploring large state spaces and computing long-horizon, sequential plans. However, these algorithms are generally challenged with complex, stochastic, and high-dimensional state spaces as well as in the presence of narrow passages, which naturally emerge in tasks that interact with the environment. Machine learning offers a promising solution for its ability to learn general policies that can handle complex interactions and high-dimensional observations. However, these policies are generally limited in horizon length. Our approach, Broadly-Exploring, Local-policy Trees (BELT), merges these two approaches to leverage the strengths of both through a task-conditioned, model-based tree search. BELT uses an RRT-inspired tree search to efficiently explore the state space. Locally, the exploration is guided by a task-conditioned, learned policy capable of performing general short-horizon tasks. This task space can be quite general and abstract; its only requirements are to be sampleable and to well-cover the space of useful tasks. This search is aided by a task-conditioned model that temporally extends dynamics propagation to allow long-horizon search and sequential reasoning over tasks. BELT is demonstrated experimentally to be able to plan long-horizon, sequential trajectories with a goal conditioned policy and generate plans that are robust.

READ FULL TEXT

page 4

page 6

page 8

page 11

page 12

page 13

page 14

page 15

research
11/18/2021

Successor Feature Landmarks for Long-Horizon Goal-Conditioned Reinforcement Learning

Operating in the real-world often requires agents to learn about a compl...
research
07/10/2021

LS3: Latent Space Safe Sets for Long-Horizon Visuomotor Control of Iterative Tasks

Reinforcement learning (RL) algorithms have shown impressive success in ...
research
03/16/2023

Efficient Learning of High Level Plans from Play

Real-world robotic manipulation tasks remain an elusive challenge, since...
research
04/22/2020

Flexible and Efficient Long-Range Planning Through Curious Exploration

Identifying algorithms that flexibly and efficiently discover temporally...
research
03/13/2020

Sparse Graphical Memory for Robust Planning

To operate effectively in the real world, artificial agents must act fro...
research
10/14/2022

Abstract-to-Executable Trajectory Translation for One-Shot Task Generalization

Training long-horizon robotic policies in complex physical environments ...
research
02/14/2019

Learn a Prior for RHEA for Better Online Planning

Rolling Horizon Evolutionary Algorithms (RHEA) are a class of online pla...

Please sign up or login with your details

Forgot password? Click here to reset