# Non-maximizing policies that fulfill multi-criterion aspirations in expectation

arXiv: https://arxiv.org/abs/2408.04385 · HTML: https://mlsanity.com/paper/2408.04385/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in RL theory and sample complexity, one of 15 directions in Deep reinforcement learning methods.
- Builds on 8 of its 21 references that are in the map.
- First posted on arXiv 8 Aug 2024.

## Placed in

- Deep reinforcement learning methods / [RL theory and sample complexity](https://mlsanity.com/deeprl/rl-theory-and-sample-complexity/)

## Builds on (most cited first, 8 of 8)

- [Concrete Problems in AI Safety](https://mlsanity.com/paper/1606.06565/) (2016)
- [Decision Transformer: Reinforcement Learning via Sequence Modeling](https://mlsanity.com/paper/2106.01345/) (2021)
- [Towards Guaranteed Safe AI: A Framework for Ensuring Robust and Reliable AI Systems](https://mlsanity.com/paper/2405.06624/) (2024)
- [Reinforcement Learning with Convex Constraints](https://mlsanity.com/paper/1906.09323/) (2019)
- [Reinforcement Learning through Active Inference](https://mlsanity.com/paper/2002.12636/) (2020)
- [Invariance in Policy Optimisation and Partial Identifiability in Reward Learning](https://mlsanity.com/paper/2203.07475/) (2022)
- [Generalization Analogies: A Testbed for Generalizing AI Oversight to Hard-To-Measure Domains](https://mlsanity.com/paper/2311.07723/) (2023)
- [On The Expressivity of Objective-Specification Formalisms in Reinforcement Learning](https://mlsanity.com/paper/2310.11840/) (2023)

## Abstract (arXiv)

In dynamic programming and reinforcement learning, the policy for the sequential decision making of an agent in a stochastic environment is usually determined by expressing the goal as a scalar reward function and seeking a policy that maximizes the expected total reward. However, many goals that humans care about naturally concern multiple aspects of the world, and it may not be obvious how to condense those into a single reward function. Furthermore, maximization suffers from specification gaming, where the obtained policy achieves a high expected total reward in an unintended way, often taking extreme or nonsensical actions. Here we consider finite acyclic Markov Decision Processes with multiple distinct evaluation metrics, which do not necessarily represent quantities that the user wants to be maximized. We assume the task of the agent is to ensure that the vector of expected totals of the evaluation metrics falls into some given convex set, called the aspiration set. Our algorithm guarantees that this task is fulfilled by using simplices to approximate feasibility sets and propagate aspirations forward while ensuring they remain feasible. It has complexity linear in the number of possible state-action-successor triples and polynomial in the number of evaluation metrics. Moreover, the explicitly non-maximizing nature of the chosen policy and goals yields additional degrees of freedom, which can be used to apply heuristic safety criteria to the choice of actions. We discuss several such safety criteria that aim to steer the agent towards more conservative behavior.