Importance of Environment Design in Reinforcement Learning: A Study of a Robotic Environment

02/20/2021
by   Mónika Farsang, et al.
0

An in-depth understanding of the particular environment is crucial in reinforcement learning (RL). To address this challenge, the decision-making process of a mobile collaborative robotic assistant modeled by the Markov decision process (MDP) framework is studied in this paper. The optimal state-action combinations of the MDP are calculated with the non-linear Bellman optimality equations. This system of equations can be solved with relative ease by the computational power of Wolfram Mathematica, where the obtained optimal action-values results point to the optimal policy. Unlike other RL algorithms, this methodology does not approximate the optimal behavior, it provides the exact, explicit solution, which provides a strong foundation for our study. With this, we offer new insights into understanding the action selection mechanisms in RL. During the analysis of the robotic environment, we present various small modifications on the very same schema that lead to different optimal policies. Finally, we emphasize that beyond building efficient RL algorithms, only the proper design of the environment can ensure the desired results.

READ FULL TEXT
research
09/02/2020

A reinforcement learning approach to hybrid control design

In this paper we design hybrid control policies for hybrid systems whose...
research
12/21/2019

Online Reinforcement Learning of Optimal Threshold Policies for Markov Decision Processes

Markov Decision Process (MDP) problems can be solved using Dynamic Progr...
research
05/30/2017

Universal Reinforcement Learning Algorithms: Survey and Experiments

Many state-of-the-art reinforcement learning (RL) algorithms typically a...
research
11/29/2019

When Blockchain Meets AI: Optimal Mining Strategy Achieved By Machine Learning

This work applies reinforcement learning (RL) from the AI machine learni...
research
05/14/2022

QHD: A brain-inspired hyperdimensional reinforcement learning algorithm

Reinforcement Learning (RL) has opened up new opportunities to solve a w...
research
04/15/2020

Reinforcement Learning in a Physics-Inspired Semi-Markov Environment

Reinforcement learning (RL) has been demonstrated to have great potentia...
research
03/13/2019

Task-oriented Design through Deep Reinforcement Learning

We propose a new low-cost machine-learning-based methodology which assis...

Please sign up or login with your details

Forgot password? Click here to reset