Deep Reinforcement Learning for Dexterous Manipulation with Concept Networks

09/20/2017
by   Aditya Gudimella, et al.
0

Deep reinforcement learning yields great results for a large array of problems, but models are generally retrained anew for each new problem to be solved. Prior learning and knowledge are difficult to incorporate when training new models, requiring increasingly longer training as problems become more complex. This is especially problematic for problems with sparse rewards. We provide a solution to these problems by introducing Concept Network Reinforcement Learning (CNRL), a framework which allows us to decompose problems using a multi-level hierarchy. Concepts in a concept network are reusable, and flexible enough to encapsulate feature extractors, skills, or other concept networks. With this hierarchical learning approach, deep reinforcement learning can be used to solve complex tasks in a modular way, through problem decomposition. We demonstrate the strength of CNRL by training a model to grasp a rectangular prism and precisely stack it on top of a cube using a gripper on a Kinova JACO arm, simulated in MuJoCo. Our experiments show that our use of hierarchy results in a 45x reduction in environment interactions compared to the state-of-the-art on this task.

READ FULL TEXT

page 6

page 9

page 12

research
12/12/2017

Deep Reinforcement Learning Boosted by External Knowledge

Recent improvements in deep reinforcement learning have allowed to solve...
research
03/04/2019

Model Primitive Hierarchical Lifelong Reinforcement Learning

Learning interpretable and transferable subpolicies and performing task ...
research
04/19/2021

Deep Reinforcement Learning in a Monetary Model

We propose using deep reinforcement learning to solve dynamic stochastic...
research
04/21/2022

Learning how to Interact with a Complex Interface using Hierarchical Reinforcement Learning

Hierarchical Reinforcement Learning (HRL) allows interactive agents to d...
research
05/16/2020

Concept Learning in Deep Reinforcement Learning

Deep reinforcement learning techniques have shown to be a promising path...
research
11/20/2019

Deep Reinforcement Learning with Explicitly Represented Knowledge and Variable State and Action Spaces

We focus on a class of real-world domains, where gathering hierarchical ...
research
06/29/2021

DRILL– Deep Reinforcement Learning for Refinement Operators in 𝒜ℒ𝒞

Approaches based on refinement operators have been successfully applied ...

Please sign up or login with your details

Forgot password? Click here to reset