Adaptable Automation with Modular Deep Reinforcement Learning and Policy Transfer

11/27/2020
by   Zohreh Raziei, et al.
0

Recent advances in deep Reinforcement Learning (RL) have created unprecedented opportunities for intelligent automation, where a machine can autonomously learn an optimal policy for performing a given task. However, current deep RL algorithms predominantly specialize in a narrow range of tasks, are sample inefficient, and lack sufficient stability, which in turn hinder their industrial adoption. This article tackles this limitation by developing and testing a Hyper-Actor Soft Actor-Critic (HASAC) RL framework based on the notions of task modularization and transfer learning. The goal of the proposed HASAC is to enhance the adaptability of an agent to new tasks by transferring the learned policies of former tasks to the new task via a "hyper-actor". The HASAC framework is tested on a new virtual robotic manipulation benchmark, Meta-World. Numerical experiments show superior performance by HASAC over state-of-the-art deep RL algorithms in terms of reward value, success rate, and task completion time.

READ FULL TEXT

page 17

page 19

research
06/06/2019

Improving Exploration in Soft-Actor-Critic with Normalizing Flows Policies

Deep Reinforcement Learning (DRL) algorithms for continuous action space...
research
04/21/2022

Optimizing Nitrogen Management with Deep Reinforcement Learning and Crop Simulations

Nitrogen (N) management is critical to sustain soil fertility and crop p...
research
02/25/2020

Simultaneously Evolving Deep Reinforcement Learning Models using Multifactorial Optimization

In recent years, Multifactorial Optimization (MFO) has gained a notable ...
research
11/11/2022

Efficient Deep Reinforcement Learning with Predictive Processing Proximal Policy Optimization

Advances in reinforcement learning (RL) often rely on massive compute re...
research
05/02/2017

Navigating Intersections with Autonomous Vehicles using Deep Reinforcement Learning

Providing an efficient strategy to navigate safely through unsignaled in...
research
03/08/2022

Robot Learning of Mobile Manipulation with Reachability Behavior Priors

Mobile Manipulation (MM) systems are ideal candidates for taking up the ...
research
06/23/2021

Coarse-to-Fine Q-attention: Efficient Learning for Visual Robotic Manipulation via Discretisation

Reflecting on the last few years, the biggest breakthroughs in deep rein...

Please sign up or login with your details

Forgot password? Click here to reset