# Mitigating Negative Side Effects via Environment Shaping

arXiv: https://arxiv.org/abs/2102.07017 · HTML: https://mlsanity.com/paper/2102.07017/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 17 references that are in the map.
- First posted on arXiv 13 Feb 2021.

## Builds on (most cited first, 4 of 4)

- [Concrete Problems in AI Safety](https://mlsanity.com/paper/1606.06565/) (2016)
- [Inverse Reward Design](https://mlsanity.com/paper/1711.02827/) (2017)
- [Preferences Implicit in the State of the World](https://mlsanity.com/paper/1902.04198/) (2019)
- [Avoiding Negative Side Effects due to Incomplete Knowledge of AI Systems](https://mlsanity.com/paper/2008.12146/) (2020)

## Built on by (most cited first, 2 of 2)

- [Reducing Human-Robot Goal State Divergence with Environment Design](https://mlsanity.com/paper/2404.15184/) (2024)
- [Adaptive Querying for Reward Learning from Human Feedback](https://mlsanity.com/paper/2412.07990/) (2024)

## Abstract (arXiv)

Agents operating in unstructured environments often produce negative side effects (NSE), which are difficult to identify at design time. While the agent can learn to mitigate the side effects from human feedback, such feedback is often expensive and the rate of learning is sensitive to the agent's state representation. We examine how humans can assist an agent, beyond providing feedback, and exploit their broader scope of knowledge to mitigate the impacts of NSE. We formulate this problem as a human-agent team with decoupled objectives. The agent optimizes its assigned task, during which its actions may produce NSE. The human shapes the environment through minor reconfiguration actions so as to mitigate the impacts of the agent's side effects, without affecting the agent's ability to complete its assigned task. We present an algorithm to solve this problem and analyze its theoretical properties. Through experiments with human subjects, we assess the willingness of users to perform minor environment modifications to mitigate the impacts of NSE. Empirical evaluation of our approach shows that the proposed framework can successfully mitigate NSE, without affecting the agent's ability to complete its assigned task.