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

arXiv: https://arxiv.org/abs/2106.02617 · HTML: https://mlsanity.com/paper/2106.02617/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 23 references that are in the map.
- First posted on arXiv 4 Jun 2021.

## Builds on (most cited first, 12 of 12)

- [Concrete Problems in AI Safety](https://mlsanity.com/paper/1606.06565/) (2016)
- [Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms](https://mlsanity.com/paper/1911.10635/) (2019)
- [Penalizing side effects using stepwise relative reachability](https://mlsanity.com/paper/1806.01186/) (2018)
- [Conservative Agency via Attainable Utility Preservation](https://mlsanity.com/paper/1902.09725/) (2019)
- [Avoiding Side Effects By Considering Future Tasks](https://mlsanity.com/paper/2010.07877/) (2020)
- [AvE: Assistance via Empowerment](https://mlsanity.com/paper/2006.14796/) (2020)
- [Avoiding Side Effects in Complex Environments](https://mlsanity.com/paper/2006.06547/) (2020)
- [SafeLife 1.0: Exploring Side Effects in Complex Environments](https://mlsanity.com/paper/1912.01217/) (2019)
- [Towards Empathic Deep Q-Learning](https://mlsanity.com/paper/1906.10918/) (2019)
- [Towards the Role of Theory of Mind in Explanation](https://mlsanity.com/paper/2005.02963/) (2020)
- [Helpfulness as a Key Metric of Human-Robot Collaboration](https://mlsanity.com/paper/2010.04914/) (2020)
- [Towards Empathetic Planning](https://mlsanity.com/paper/1906.06436/) (2019)

## Built on by (most cited first, 1 of 1)

- [EMOTE: An Explainable architecture for Modelling the Other Through Empathy](https://mlsanity.com/paper/2306.00295/) (2023)

## Abstract (arXiv)

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.