A Low-Cost Ethics Shaping Approach for Designing Reinforcement Learning Agents

12/12/2017
by   Yueh-Hua Wu, et al.
1

This paper proposes a low-cost, easily realizable strategy to equip a reinforcement learning (RL) agent the capability of behaving ethically. Our model allows the designers of RL agents to solely focus on the task to achieve, without having to worry about the implementation of multiple trivial ethical patterns to follow. Based on the assumption that the majority of human behavior, regardless which goals they are achieving, is ethical, our design integrates human policy with the RL policy to achieve the target objective with less chance of violating the ethical code that human beings normally obey.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/30/2014

Do Artificial Reinforcement-Learning Agents Matter Morally?

Artificial reinforcement learning (RL) is a widely used technique in art...
research
03/30/2022

Reinforcement Learning Guided by Provable Normative Compliance

Reinforcement learning (RL) has shown promise as a tool for engineering ...
research
06/08/2020

Reinforcement Learning Under Moral Uncertainty

An ambitious goal for artificial intelligence is to create agents that b...
research
03/13/2019

Task-oriented Design through Deep Reinforcement Learning

We propose a new low-cost machine-learning-based methodology which assis...
research
10/12/2018

Bayesian Inference of Self-intention Attributed by Observer

Most of agents that learn policy for tasks with reinforcement learning (...
research
08/08/2020

Hierarchial Reinforcement Learning in StarCraft II with Human Expertise in Subgoals Selection

This work is inspired by recent advances in hierarchical reinforcement l...
research
06/22/2018

Many-Goals Reinforcement Learning

All-goals updating exploits the off-policy nature of Q-learning to updat...

Please sign up or login with your details

Forgot password? Click here to reset