Be Considerate: Objectives, Side Effects, and Deciding How to Act

by   Parand Alizadeh Alamdari, et al.

Recent work in AI safety has highlighted that in sequential decision making, objectives are often underspecified or incomplete. This gives discretion to the acting agent to realize the stated objective in ways that may result in undesirable outcomes. We contend that to learn to act safely, a reinforcement learning (RL) agent should include contemplation of the impact of its actions on the wellbeing and agency of others in the environment, including other acting agents and reactive processes. We endow RL agents with the ability to contemplate such impact by augmenting their reward based on expectation of future return by others in the environment, providing different criteria for characterizing impact. We further endow these agents with the ability to differentially factor this impact into their decision making, manifesting behavior that ranges from self-centred to self-less, as demonstrated by experiments in gridworld environments.



There are no comments yet.


page 1

page 2

page 3

page 4


Learning to Incentivize Other Learning Agents

The challenge of developing powerful and general Reinforcement Learning ...

Reinforcement Learning-based Autoscaling of Workflows in the Cloud: A Survey

Reinforcement Learning (RL) has demonstrated a great potential for autom...

Text-based RL Agents with Commonsense Knowledge: New Challenges, Environments and Baselines

Text-based games have emerged as an important test-bed for Reinforcement...

Optimal Farsighted Agents Tend to Seek Power

Some researchers have speculated that capable reinforcement learning (RL...

The Value of Information When Deciding What to Learn

All sequential decision-making agents explore so as to acquire knowledge...

Pavlovian Signalling with General Value Functions in Agent-Agent Temporal Decision Making

In this paper, we contribute a multi-faceted study into Pavlovian signal...

Decentralized Decision-Making Over Multi-Task Networks

In important applications involving multi-task networks with multiple ob...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.