# SafeLife 1.0: Exploring Side Effects in Complex Environments

arXiv: https://arxiv.org/abs/1912.01217 · HTML: https://mlsanity.com/paper/1912.01217/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Dec 2019.

## Built on by (most cited first, 8 of 8)

- [Unsolved Problems in ML Safety](https://mlsanity.com/paper/2109.13916/) (2021)
- [Forecasting Future World Events with Neural Networks](https://mlsanity.com/paper/2206.15474/) (2022)
- [What Would Jiminy Cricket Do? Towards Agents That Behave Morally](https://mlsanity.com/paper/2110.13136/) (2021)
- [A Survey of Safe Reinforcement Learning and Constrained MDPs: A Technical Survey on Single-Agent and Multi-Agent Safety](https://mlsanity.com/paper/2505.17342/) (2025)
- [Formalizing the Problem of Side Effect Regularization](https://mlsanity.com/paper/2206.11812/) (2022)
- [Be Considerate: Objectives, Side Effects, and Deciding How to Act](https://mlsanity.com/paper/2106.02617/) (2021)
- [Safer Reinforcement Learning through Transferable Instinct Networks](https://mlsanity.com/paper/2107.06686/) (2021)
- [HarvestBench: Measuring Whether LLM Agents Will Pay to Avoid Killing Animals](https://mlsanity.com/paper/2609.04444/) (2026)

## Abstract (arXiv)

We present SafeLife, a publicly available reinforcement learning environment that tests the safety of reinforcement learning agents. It contains complex, dynamic, tunable, procedurally generated levels with many opportunities for unsafe behavior. Agents are graded both on their ability to maximize their explicit reward and on their ability to operate safely without unnecessary side effects. We train agents to maximize rewards using proximal policy optimization and score them on a suite of benchmark levels. The resulting agents are performant but not safe -- they tend to cause large side effects in their environments -- but they form a baseline against which future safety research can be measured.