Reinforcement Control with Hierarchical Backpropagated Adaptive Critics

12/08/2015
by   John W. Jameson, et al.
0

Present incremental learning methods are limited in the ability to achieve reliable credit assignment over a large number time steps (or events). However, this situation is typical for cases where the dynamical system to be controlled requires relatively frequent control updates in order to maintain stability or robustness yet has some action-consequences which must be established over relatively long periods of time. To address this problem, the learning capabilities of a control architecture comprised of two Backpropagated Adaptive Critics (BACs) in a two-level hierarchy with continuous actions are explored. The high-level BAC updates less frequently than the low-level BAC and controls the latter to some degree. The response of the low-level to high-level signals can either be determined a priori or it can emerge during learning. A general approach called Response Induction Learning is introduced to address the latter case.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/16/2019

Conditions for Hierarchical Supervisory Control under Partial Observation

The fundamental problem in hierarchical supervisory control under partia...
research
12/24/2022

SHIRO: Soft Hierarchical Reinforcement Learning

Hierarchical Reinforcement Learning (HRL) algorithms have been demonstra...
research
10/26/2020

Learning Concepts from Sensor Data of a Mobile Robot

Machine learning can be a most valuable tool for improving the flexibili...
research
02/06/2020

Temporal-adaptive Hierarchical Reinforcement Learning

Hierarchical reinforcement learning (HRL) helps address large-scale and ...
research
04/05/2022

Learning Pneumatic Non-Prehensile Manipulation with a Mobile Blower

We investigate pneumatic non-prehensile manipulation (i.e., blowing) as ...
research
01/11/2019

Low Level Control of a Quadrotor with Deep Model-Based Reinforcement learning

Generating low-level robot controllers often requires manual parameters ...
research
12/31/2022

Action Codes

We provide a new perspective on the problem how high-level state machine...

Please sign up or login with your details

Forgot password? Click here to reset