DeepAI AI Chat
Log In Sign Up

Adaptable Automation with Modular Deep Reinforcement Learning and Policy Transfer

by   Zohreh Raziei, et al.

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.


page 17

page 19


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

Deep Reinforcement Learning (DRL) algorithms for continuous action space...

Optimizing Nitrogen Management with Deep Reinforcement Learning and Crop Simulations

Nitrogen (N) management is critical to sustain soil fertility and crop p...

Simultaneously Evolving Deep Reinforcement Learning Models using Multifactorial Optimization

In recent years, Multifactorial Optimization (MFO) has gained a notable ...

Efficient meta reinforcement learning via meta goal generation

Meta reinforcement learning (meta-RL) is able to accelerate the acquisit...

Navigating Intersections with Autonomous Vehicles using Deep Reinforcement Learning

Providing an efficient strategy to navigate safely through unsignaled in...

Efficient Deep Reinforcement Learning with Predictive Processing Proximal Policy Optimization

Advances in reinforcement learning (RL) often rely on massive compute re...

Robot Learning of Mobile Manipulation with Reachability Behavior Priors

Mobile Manipulation (MM) systems are ideal candidates for taking up the ...